© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67338
    Prev
    Next
    INDEX
    Explanations

    function calls

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

    This neuron detects code tokens representing the " ); " sequence—that is, closing-parenthesis + semicolon often ending a function or method call.

    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
    вольно
    -0.97
    ـ
    -0.96
    ЧА
    -0.93
    〉
    -0.93
    gae
    -0.93
    การ
    -0.93
    मान
    -0.92
    ی
    -0.88
    ctil
    -0.87
    焼く
    -0.87
    POSITIVE LOGITS
     jälkeen
    1.09
     naše
    0.95
     or
    0.91
     quedará
    0.90
     možnosti
    0.90
     those
    0.88
    Lettuce
    0.86
     était
    0.85
     was
    0.85
     była
    0.85
    Activations Density 0.014%

    No Known Activations