© 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. 22209
    Prev
    Next
    INDEX
    Explanations

    Chilli, Gilli, Møller

    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
    絎
    -3.52
    ......”
    -2.75
     丁目
    -2.73
    sandalia
    -2.67
    pulseira
    -2.63
    ዡ
    -2.63
    毟
    -2.59
    퐼
    -2.58
    銲
    -2.56
     株式
    -2.55
    POSITIVE LOGITS
    –
    2.91
    —
    2.89
     "
    2.80
    o
    2.73
    '
    2.70
    l
    2.70
    [
    2.59
    en
    2.48
     ``
    2.39
    に
    2.39
    Activations Density 0.007%

    No Known Activations