© 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. 128971
    Prev
    Next
    INDEX
    Explanations

    San

    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
    鹮
    -3.75
     If
    -3.02
    厹
    -2.91
    ؿ
    -2.73
    に見える
    -2.61
    髎
    -2.56
    身边的
    -2.56
     lidé
    -2.50
    眥
    -2.48
    al
    -2.44
    POSITIVE LOGITS
    N
    4.06
    D
    3.27
    L
    2.94
    F
    2.88
    H
    2.80
    E
    2.75
    </b>
    2.75
    T
    2.73
    A
    2.56
    M
    2.56
    Activations Density 0.020%

    No Known Activations