© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25156
    Prev
    Next
    INDEX
    Explanations

    function parameters or arguments

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

    The neuron fires on open‐parenthesis tokens “(” used to begin argument lists (e.g. in function or macro calls/definitions).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     other
    -1.05
     without
    -1.03
     then
    -1.00
    
    -0.98
     still
    -0.96
     as
    -0.94
     solely
    -0.93
    دود
    -0.90
     any
    -0.90
     fotografias
    -0.90
    POSITIVE LOGITS
    ENNIS
    0.91
     Cle
    0.87
    ANSION
    0.85
    я
    0.84
    IKES
    0.83
     topp
    0.83
     MaterialApp
    0.82
    ENT
    0.82
     GEN
    0.81
     jurid
    0.81
    Activations Density 0.015%

    No Known Activations