© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    function calls and variable declarations

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

    This neuron identifies programming code elements—especially function definitions and calls signaled by the “function” keyword or an identifier immediately followed by parentheses.

    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
    ículas
    -1.03
     causando
    -1.02
     Stadion
    -0.99
     candidat
    -0.97
    izard
    -0.96
     การ์ตูน
    -0.96
    ваем
    -0.93
    ¡¡
    -0.91
    enaire
    -0.91
     olimp
    -0.89
    POSITIVE LOGITS
     example
    1.54
     actuales
    1.16
     reikia
    1.11
     examples
    1.09
     today
    1.05
     professionali
    1.01
     specifiche
    1.01
     tė
    0.97
     exemplary
    0.96
    具体的な
    0.95
    Activations Density 0.010%

    No Known Activations