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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 680
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
     スリム
    -1.77
    
    -1.73
     まる
    -1.73
    
    -1.72
     ポーチ
    -1.71
    sandalia
    -1.70
    謦
    -1.66
     procédé
    -1.65
     カットソー
    -1.64
    읗
    -1.63
    POSITIVE LOGITS
     and
    3.14
     in
    2.88
     by
    2.77
     for
    2.50
     as
    2.13
     at
    2.08
     or
    2.08
     because
    2.02
     on
    1.96
     if
    1.96
    Activations Density 0.170%

    No Known Activations