© 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. 86204
    Prev
    Next
    INDEX
    Explanations

    Fuji, JDBC, KeyUp, kain, Gump

    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
    
    -2.50
    os
    -2.48
     violen
    -2.27
    d
    -2.27
    ⢌
    -2.17
     the
    -2.14
    ?
    -2.14
    也太
    -2.09
    -2.08
    this
    -2.06
    POSITIVE LOGITS
    嵛
    2.89
    一场
    2.69
     Their
    2.66
    嵙
    2.59
    er
    2.52
    龊
    2.50
     obligación
    2.47
     думал
    2.38
    )}]{
    2.36
    olkata
    2.34
    Activations Density 0.006%

    No Known Activations