© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10243
    Prev
    Next
    INDEX
    Explanations

    javascript function definitions

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

    the keyword "function" when it appears in JavaScript code, particularly in function declarations and definitions.

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

    This neuron strongly activates on the JavaScript “function” keyword (i.e. function definitions).

    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
    ~,
    -1.63
    ‟
    -1.49
    嗵
    -1.48
     drenaje
    -1.47
    ()=>{
    -1.47
    眎
    -1.47
    ∵
    -1.45
    )--
    -1.44
     dunque
    -1.43
    ~.
    -1.41
    POSITIVE LOGITS
     in
    2.02
    .
    1.55
    geſ
    1.52
     at
    1.45
     MessageBoxIcon
    1.38
     of
    1.38
     också
    1.37
     For
    1.34
    *
    1.34
      
    1.33
    Activations Density 0.153%

    No Known Activations