© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12629
    Prev
    Next
    INDEX
    Explanations

    TS version

    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
    是
    -1.88
    $
    -1.80
    建议
    -1.66
    ↵↵
    -1.64
    は
    -1.59
     необходи
    -1.59
    癭
    -1.57
     signif
    -1.53
    olingo
    -1.52
    存储
    -1.50
    POSITIVE LOGITS
     other
    2.20
     similar
    1.95
     with
    1.80
     kleinen
    1.78
    utella
    1.77
     powodu
    1.64
     Believe
    1.63
    asgi
    1.63
     Two
    1.62
     другими
    1.62
    Activations Density 0.000%

    No Known Activations