© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102670
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    semicolons at the end of statements in programming 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
     only
    -1.73
    /
    -1.70
     even
    -1.50
     five
    -1.48
     all
    -1.48
     fête
    -1.45
    (
    -1.45
    翃
    -1.39
     other
    -1.38
    cím
    -1.38
    POSITIVE LOGITS
     are
    1.62
    ↵↵
    1.52
     Bemerkungen
    1.46
     sebuah
    1.43
     estrena
    1.36
    欷
    1.34
    芣
    1.34
     eventualmente
    1.34
    不可能
    1.33
     accesible
    1.31
    Activations Density 0.011%

    No Known Activations