© 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. 34-GEMMASCOPE-RES-131K
    7. 119167
    Prev
    Next
    INDEX
    Explanations

    probability

    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_34/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
     Eleventh
    -0.79
    セブン
    -0.77
     Lian
    -0.77
    म
    -0.73
    ولات
    -0.73
     Eleven
    -0.73
    مة
    -0.72
    ಮ
    -0.72
     Xs
    -0.72
     Tenth
    -0.71
    POSITIVE LOGITS
     FontWeight
    0.90
    bew
    0.71
    高效
    0.69
     TextView
    0.68
     sci
    0.67
    xffff
    0.67
     Studium
    0.67
     minhas
    0.66
    assertTrue
    0.66
    Prob
    0.66
    Activations Density 0.452%

    No Known Activations