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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 389
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Are" or "Their"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    있
    1.13
     কিন্ত
    1.05
    니
    0.93
    THING
    0.90
     visto
    0.89
    ᙱ
    0.88
    ᇂ
    0.88
     vogliono
    0.85
    借助
    0.84
    ﻱ
    0.84
    POSITIVE LOGITS
    ان
    1.03
    न
    0.89
    ים
    0.88
    an
    0.79
    ant
    0.78
    sion
    0.77
    quela
    0.75
    ین
    0.75
    ль
    0.74
    ian
    0.72
    Activations Density 0.076%

    No Known Activations