© 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. 111884
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    code syntax elements like keywords, declarations, and operators in programming languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on programming‐language tokens—keywords, types, identifiers, and string literal contents—essentially picking out code syntax elements in source excerpts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     kterou
    -1.47
    pastebin
    -1.46
     forskjellige
    -1.46
     данного
    -1.45
    cuidado
    -1.43
     červen
    -1.41
    rmk
    -1.41
    
    -1.40
     bedien
    -1.38
    cloudf
    -1.36
    POSITIVE LOGITS
    {~
    1.70
     it
    1.49
    in
    1.43
     by
    1.34
     for
    1.32
    馘
    1.28
     campana
    1.28
    🎖
    1.27
    foreach
    1.22
    也
    1.22
    Activations Density 0.085%

    No Known Activations