© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15335
    Prev
    Next
    INDEX
    Explanations

    JavaScript module require calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    All
    -1.87
     допомогою
    -1.82
    Just
    -1.75
    ﾈ
    -1.73
    🪲
    -1.71
    An
    -1.69
    How
    -1.68
     just
    -1.68
    幾天
    -1.66
     profundo
    -1.65
    POSITIVE LOGITS
    逦
    2.16
    又一次
    1.71
    lahoma
    1.60
    是要
    1.59
     puisqu
    1.58
     vítima
    1.57
    GHI
    1.50
    硨
    1.49
    able
    1.49
    in
    1.48
    Activations Density 0.009%

    No Known Activations