© 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. 59735
    Prev
    Next
    INDEX
    Explanations

    windshield wipers or MLA

    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
    缡
    -2.17
    WRENCE
    -2.11
    臯
    -2.03
    ysql
    -1.95
    下一篇
    -1.95
    郅
    -1.94
     escultura
    -1.94
     Mitteln
    -1.92
     sorgfäl
    -1.90
    珑
    -1.88
    POSITIVE LOGITS
    I
    2.69
    s
    2.36
    '
    2.03
    F
    2.00
    D
    1.94
    U
    1.81
     aseguró
    1.79
    Q
    1.77
     neki
    1.73
    ?”
    1.69
    Activations Density 0.002%

    No Known Activations