© 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-262K
    7. 172790
    Prev
    Next
    INDEX
    Explanations

    unit dimensions

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

    topic or category names

    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_262k_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
    $)
    0.54
    ناب
    0.52
    ){}
    0.50
    _);
    0.50
    Hud
    0.48
    testAvg
    0.48
    VarArgs
    0.48
    InterfaceLine
    0.47
    𒌋
    0.47
    jumping
    0.47
    POSITIVE LOGITS
    0.67
     merged
    0.53
     Theoret
    0.50
     Merge
    0.47
     sano
    0.47
    s
    0.47
    se
    0.46
     Kanada
    0.46
    signals
    0.46
    全年
    0.45
    Activations Density 0.001%

    No Known Activations