© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38228
    Prev
    Next
    INDEX
    Explanations

    function calls

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

    This neuron responds to the names of definitions in code—i.e. class, method, constructor, or function identifiers at their declaration points.

    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
     of
    -1.48
     for
    -1.33
     특
    -1.09
     Näch
    -1.03
     их
    -1.00
    口气
    -0.94
     instituições
    -0.92
     теперь
    -0.92
     ہے۔
    -0.92
     versions
    -0.91
    POSITIVE LOGITS
    ()
    1.54
    ziert
    1.20
     вашу
    1.00
    льт
    1.00
     linkovi
    0.99
    劻
    0.97
     muchacha
    0.96
    (';
    0.96
     halus
    0.94
     trei
    0.94
    Activations Density 0.015%

    No Known Activations