© 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. 25670
    Prev
    Next
    INDEX
    Explanations

    programming terms and identifiers

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

    The neuron fires on code‐identifier tokens—names of modules, packages, classes, types, or other library entities in source code.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    рія
    -0.96
    Expertise
    -0.91
    Herbal
    -0.90
    ADO
    -0.89
    λίου
    -0.86
     asla
    -0.86
     szczególnie
    -0.86
     informaci
    -0.85
     Dopo
    -0.84
    餸
    -0.84
    POSITIVE LOGITS
    ：</
    0.77
    有意
    0.75
     brasileiros
    0.74
     Kunden
    0.71
    something
    0.71
     $-$
    0.70
     поле
    0.70
     naudoti
    0.69
     ốp
    0.69
     accompanying
    0.69
    Activations Density 0.022%

    No Known Activations