© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16631
    Prev
    Next
    INDEX
    Explanations

    code files and programming languages

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

    This neuron fires on tokens that name or signal code/script file types and technical identifiers—e.g. file‐extension markers like “.sh”, “.py”, “php” or double-underscore Python magic methods.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     prior
    -0.97
    だけでなく
    -0.91
     others
    -0.87
     duża
    -0.87
     his
    -0.87
    siyah
    -0.86
    ことが多い
    -0.86
     mehrerer
    -0.85
    );
    -0.84
     echte
    -0.84
    POSITIVE LOGITS
    さんに
    1.26
     sebaik
    1.09
     used
    1.05
     -
    1.04
     лютого
    1.03
     estremamente
    1.03
     barcel
    1.02
     vinyle
    0.99
     janu
    0.98
     abbastanza
    0.97
    Activations Density 0.061%

    No Known Activations