© 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. 38855
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
     этом
    -2.14
    饜
    -2.11
     latter
    -1.94
    雠
    -1.88
    оргаш
    -1.82
     exemplaires
    -1.81
    ższych
    -1.80
    槼
    -1.75
    糴
    -1.75
     بشه
    -1.73
    POSITIVE LOGITS
     a
    1.91
    ž
    1.81
     the
    1.77
     by
    1.67
     nejs
    1.66
    ные
    1.65
     Of
    1.65
     How
    1.63
    、
    1.60
     ofta
    1.52
    Activations Density 0.015%

    No Known Activations