© 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. 102907
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite

    opening parentheses in function definitions and calls in JavaScript/TypeScript code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    趼
    -2.00
    ここは
    -1.98
    ↵↵
    -1.84
    
    -1.80
     unending
    -1.77
     exacting
    -1.74
     $^{\
    -1.74
    也很
    -1.70
    也
    -1.70
     denselben
    -1.70
    POSITIVE LOGITS
     it
    2.56
     in
    2.02
     you
    1.91
     through
    1.86
    していました
    1.80
     without
    1.80
    梘
    1.77
    ナメント
    1.76
     with
    1.75
    中心的
    1.75
    Activations Density 0.005%

    No Known Activations