© 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. 11482
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    semicolons in code, particularly at the end of statements in JavaScript and similar programming languages.

    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
     or
    -1.88
     when
    -1.71
     at
    -1.70
     then
    -1.67
     after
    -1.64
    4
    -1.61
     other
    -1.58
     only
    -1.57
     especially
    -1.56
     between
    -1.52
    POSITIVE LOGITS
     constater
    1.84
     beter
    1.80
     kanton
    1.70
     vider
    1.66
     Gez
    1.66
     juc
    1.63
     ovale
    1.59
     infrar
    1.54
    expandindo
    1.53
     simpel
    1.52
    Activations Density 0.022%

    No Known Activations