© 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. 10-GEMMASCOPE-RES-131K
    7. 102290
    Prev
    Next
    INDEX
    Explanations

    programming language punctuation

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

    semicolons in programming code, particularly in loops and variable declarations.

    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
     '
    -1.92
     was
    -1.85
     who
    -1.77
     }^{
    -1.56
     \
    -1.55
     />
    -1.52
     "
    -1.51
    拶
    -1.51
     retrouve
    -1.51
     Töchter
    -1.48
    POSITIVE LOGITS
    焢
    2.17
     hunde
    2.05
    灕
    1.92
     diki
    1.79
     kapak
    1.77
     filmi
    1.73
     teater
    1.72
    odziel
    1.71
     melu
    1.70
     komik
    1.70
    Activations Density 0.112%

    No Known Activations