© 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. 72122
    Prev
    Next
    INDEX
    Explanations

    function calls

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

    This neuron detects programming identifiers (function or variable names) in code snippets.

    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
    several
    -1.73
     Dinas
    -1.69
    apparently
    -1.68
    provides
    -1.64
     mediocre
    -1.64
     sooo
    -1.63
    mainly
    -1.63
    primarily
    -1.61
     soooo
    -1.61
    perhaps
    -1.61
    POSITIVE LOGITS
     on
    2.34
     with
    2.17
     when
    2.00
     through
    1.97
     by
    1.91
     after
    1.89
     first
    1.89
     does
    1.84
     while
    1.77
     focusing
    1.77
    Activations Density 0.005%

    No Known Activations