© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31661
    Prev
    Next
    INDEX
    Explanations

    JavaScript module exports

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

    This neuron recognizes the Babel-generated CommonJS “interop” boilerplate (the `exports.__esModule = true` and `_interopRequireDefault` function code) that wraps ES module imports.

    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
     more
    -0.80
     eikä
    -0.72
     concluded
    -0.71
     почина
    -0.70
    يدي
    -0.69
     at
    -0.69
     geg
    -0.69
    digans
    -0.69
    Being
    -0.68
     மூ
    -0.68
    POSITIVE LOGITS
     exports
    1.05
    interopRequire
    0.98
    esModule
    0.96
     module
    0.95
    module
    0.94
     MODULE
    0.94
     export
    0.93
    exports
    0.91
     exporting
    0.90
     Module
    0.88
    Activations Density 0.007%

    No Known Activations