© 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. 34-GEMMASCOPE-RES-131K
    7. 109418
    Prev
    Next
    INDEX
    Explanations

    javascript require statements

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

    The neuron is specialized to pick out JavaScript CommonJS “require” module‐import statements (e.g. lines with var … = require(…)).

    oai_token-act-pair · o4-miniTriggered 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
    diger
    -0.77
    次回
    -0.75
     resentment
    -0.75
     gemeenten
    -0.74
    :@"
    -0.74
     pytest
    -0.74
    влека
    -0.73
    集團
    -0.72
    межу
    -0.72
     вместо
    -0.71
    POSITIVE LOGITS
     fs
    1.34
    fs
    1.30
    util
    0.98
     moment
    0.95
     Fs
    0.88
    moment
    0.85
     kue
    0.84
    ͹
    0.82
     Fabric
    0.81
    FS
    0.81
    Activations Density 0.070%

    No Known Activations