© 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. 71780
    Prev
    Next
    INDEX
    Explanations

    % llvm directives

    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
    '
    -2.09
     Ironically
    -1.77
    ;
    -1.58
     Surprisingly
    -1.58
    :
    -1.55
    辍
    -1.54
     Regardless
    -1.52
     ночи
    -1.51
    Every
    -1.48
     Both
    -1.46
    POSITIVE LOGITS
    蜮
    1.79
     thre
    1.75
    趿
    1.63
     soooo
    1.54
     Unterstützung
    1.53
     him
    1.51
    我们
    1.50
    zość
    1.48
    螄
    1.48
     hadde
    1.48
    Activations Density 0.001%

    No Known Activations