© 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. 26804
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and commas

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

    This neuron fires on code identifiers—variable names, function/method names, and attribute names—inside Python 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
     humeur
    -1.15
    ₡
    -1.13
    >");
    -1.12
    )}$,
    -1.11
     Willkommen
    -1.09
    *}{
    -1.09
     Traducción
    -1.08
     OkHttpClient
    -1.07
    lyon
    -1.07
    ?></
    -1.06
    POSITIVE LOGITS
    ↵↵↵
    1.41
    ↵↵
    1.34
    ↵
    1.31
     remain
    1.16
     can
    1.10
     useful
    1.07
     cannot
    1.06
     provide
    1.04
     Betracht
    0.99
     should
    0.98
    Activations Density 0.009%

    No Known Activations