© 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. 58859
    Prev
    Next
    INDEX
    Explanations

    essays

    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
    ’
    -2.38
    苤
    -2.22
    鸲
    -2.13
    のご紹介
    -1.95
    麁
    -1.93
    进来
    -1.88
    并没有
    -1.88
    でご
    -1.81
    癟
    -1.81
    几个人
    -1.80
    POSITIVE LOGITS
    s
    2.83
    e
    1.95
    7
    1.85
    ps
    1.84
    k
    1.83
    $
    1.77
    (
    1.77
    x
    1.76
    ad
    1.75
    [
    1.75
    Activations Density 0.012%

    No Known Activations