© 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. 21417
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis punctuation

    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
    \
    -2.56
    在
    -2.02
    f
    -1.96
    In
    -1.94
    $
    -1.91
    (
    -1.84
    雖然
    -1.82
    もしくは
    -1.77
    または
    -1.76
    或
    -1.72
    POSITIVE LOGITS
     querían
    1.91
    这一幕
    1.80
     őket
    1.77
    nitř
    1.77
    ݮ
    1.74
    ⢱
    1.71
    迥
    1.70
     joyas
    1.70
    桄
    1.69
     attentive
    1.68
    Activations Density 0.105%

    No Known Activations