© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40230
    Prev
    Next
    INDEX
    Explanations

    all

    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
    蛱
    -1.85
    creating
    -1.69
    didn
    -1.67
    could
    -1.62
     ทำ
    -1.62
    ⩖
    -1.59
     établir
    -1.58
    禟
    -1.58
     festge
    -1.58
    vato
    -1.55
    POSITIVE LOGITS
     from
    2.19
     in
    2.11
     for
    1.92
     if
    1.75
     people
    1.73
     with
    1.73
     an
    1.63
     because
    1.63
     квітня
    1.55
     not
    1.52
    Activations Density 0.065%

    No Known Activations