© 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. 22-GEMMASCOPE-RES-131K
    7. 128871
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on import statements and their module paths in source code.

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

    language imports

    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
     in
    -0.92
     then
    -0.89
     actually
    -0.88
     would
    -0.88
    弟
    -0.84
     évek
    -0.82
    年的
    -0.81
     الصيف
    -0.80
     理由
    -0.78
    然
    -0.77
    POSITIVE LOGITS
    arım
    0.89
    itäts
    0.88
     Много
    0.87
     rekla
    0.85
    踉
    0.84
    kante
    0.84
     réfrig
    0.84
    lässt
    0.82
    kowa
    0.82
    lown
    0.81
    Activations Density 0.080%

    No Known Activations