© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 9339
    Prev
    Next
    INDEX
    Explanations

    different languages' "our"

    np_acts-logits-general · gemini-2.5-flash-lite

    The pattern highlights persuasive or emphatic language in speeches, essays, and advocacy content, particularly when making moral arguments, calls to action, or establishing importance. The marked tokens typically express core values, collective identity ("us," "we"), ethical imperatives ("should," "must"), or emphasize key concepts in argumentative discourse (like "importance," "benefit," "support"). This language seeks to engage audiences emotionally and intellectually, often appearing in contexts where the speaker/writer is establishing credibility, building consensus, or urging change.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oldukça
    0.61
    /
    0.61
     presumably
    0.60
     khá
    0.60
     bzw
    0.56
     oneself
    0.56
    いろいろ
    0.54
     dianggap
    0.52
     playfully
    0.52
     dude
    0.51
    POSITIVE LOGITS
     our
    0.97
     naše
    0.92
     nossa
    0.90
     наші
    0.90
     nuestros
    0.87
     nuestra
    0.87
     हमारी
    0.86
     наши
    0.83
     mūsų
    0.83
     nossos
    0.81
    Activations Density 0.107%

    No Known Activations