© 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. 22-GEMMASCOPE-RES-131K
    7. 72354
    Prev
    Next
    INDEX
    Explanations

    excellence and praise

    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_22/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
    起床
    -2.27
    恫
    -2.25
    뀝
    -2.23
     всѣ
    -2.23
    荜
    -2.19
    뉩
    -2.14
     était
    -2.13
    埛
    -2.09
    傷害
    -2.06
    厓
    -2.06
    POSITIVE LOGITS
    .
    3.61
    [
    2.88
    Also
    2.45
    that
    2.08
    Still
    2.03
    ”
    1.99
     that
    1.98
    <
    1.95
    ،
    1.93
    Just
    1.91
    Activations Density 0.015%

    No Known Activations