© 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. 10-GEMMASCOPE-RES-131K
    7. 22492
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods

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

    The neuron fires on programming function or method names (e.g. code identifiers used in calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    "
    -1.52
     möjlighet
    -1.49
    *
    -1.36
    Its
    -1.35
    <strong>
    -1.28
    はない
    -1.27
    <h3>
    -1.25
    sees
    -1.24
     angustia
    -1.23
    富山
    -1.23
    POSITIVE LOGITS
     of
    2.72
     him
    2.03
     you
    1.82
     them
    1.57
     your
    1.56
    //};
    1.45
     it
    1.44
     himself
    1.42
     onCancelled
    1.32
     angene
    1.30
    Activations Density 0.023%

    No Known Activations