© 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. 25142
    Prev
    Next
    INDEX
    Explanations

    code constructs

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

    The neuron fires on sequences of letters and digits that look like code identifiers (variable, function, class, or module names) rather than on punctuation or keywords.

    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
     these
    -1.24
     this
    -1.15
    phem
    -1.04
     its
    -0.98
    setViewName
    -0.91
     penyebab
    -0.91
    総評
    -0.89
    ssohn
    -0.88
     стоко
    -0.87
    ="")
    -0.87
    POSITIVE LOGITS
    МІ
    1.04
    ///**
    0.96
    PAGE
    0.92
    ӱ
    0.90
     Pamph
    0.90
     financement
    0.90
    🎮
    0.90
    Apesar
    0.89
    唁
    0.87
     Dess
    0.86
    Activations Density 0.002%

    No Known Activations