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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13136
    Prev
    Next
    INDEX
    Explanations

    deictic pronouns introducing concepts

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

    purpose prediction principles statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这类
    0.61
    ల్లో
    0.46
    чиго
    0.43
     它
    0.42
    इसमें
    0.41
     ინ
    0.41
    เยอะ
    0.40
     इसमें
    0.40
     нужна
    0.40
    䢌
    0.40
    POSITIVE LOGITS
     phenomenon
    0.59
     dictum
    0.53
     Tatsache
    0.53
     hypothesis
    0.52
     assumption
    0.52
     procedure
    0.52
     statement
    0.50
     situation
    0.49
     tactic
    0.48
     fact
    0.48
    Activations Density 0.186%

    No Known Activations