© 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. 34-GEMMASCOPE-RES-131K
    4. 80796
    Prev
    Next
    INDEX
    Explanations

    correlations between subjects

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

    The neuron fires on JavaScript (and Node.js) import/require statements for the “fs” (filesystem) module.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

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

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    Node.js code that imports built-in modules—especially the filesystem module—via require statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Kh
    -0.76
    jean
    -0.71
    Candidate
    -0.71
     Opener
    -0.70
     kinderen
    -0.70
    плата
    -0.70
    Rag
    -0.69
     opener
    -0.69
     FTA
    -0.69
     epithelium
    -0.69
    POSITIVE LOGITS
    stream
    0.71
     MemoryStream
    0.68
     stream
    0.66
     William
    0.64
    лары
    0.62
    types
    0.60
    流水
    0.60
     Selby
    0.60
     chiefly
    0.60
     Tha
    0.60
    Activations Density 0.072%

    No Known Activations