© 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. 34-GEMMASCOPE-RES-131K
    7. 80830
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

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

    The neuron fires on programming‐language structural markers (e.g. punctuation like braces, parentheses, semicolons, and comment tokens) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     crime
    -0.79
    에서
    -0.75
     beers
    -0.71
     arenas
    -0.69
    Mats
    -0.68
     hers
    -0.68
    undial
    -0.67
    दै
    -0.67
    ersatz
    -0.67
    ყ
    -0.67
    POSITIVE LOGITS
     TODO
    2.97
     whom
    1.63
    whom
    1.25
     whose
    1.20
     Whom
    1.09
    \[
    1.06
     которых
    0.95
    whose
    0.90
     której
    0.90
    <code>
    0.89
    Activations Density 0.005%

    No Known Activations