© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129349
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the CommonJS “require” call (i.e. import statements using require()).

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

    require followed by module paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -2.13
     for
    -2.02
     only
    -1.79
     if
    -1.79
     this
    -1.59
     just
    -1.49
    fordshire
    -1.45
     because
    -1.45
     these
    -1.43
     setObject
    -1.38
    POSITIVE LOGITS
    łania
    1.48
     nuestras
    1.45
    妧
    1.39
    <>
    
    1.37
    ほら
    1.35
     unbelievably
    1.35
     vuestro
    1.35
     reemplazar
    1.34
    で行
    1.33
    
    1.33
    Activations Density 0.009%

    No Known Activations