© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111954
    Prev
    Next
    INDEX
    Explanations

    matching and finding data

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

    function or method names in programming code, particularly those related to matching, requests, or data retrieval operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code identifiers—especially function, method, and API names (e.g. preg_match_all, spearmanr, pearsonr, JSON, regex, split, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -2.42
     after
    -1.65
     in
    -1.58
     if
    -1.52
     to
    -1.51
     until
    -1.45
     and
    -1.45
     or
    -1.45
     from
    -1.35
     of
    -1.34
    POSITIVE LOGITS
    .
    1.30
     augmente
    1.28
    Occasionally
    1.25
    şehir
    1.23
     merveilleux
    1.22
     relâche
    1.22
     alho
    1.21
    🥉
    1.18
     sué
    1.17
     pauv
    1.17
    Activations Density 0.033%

    No Known Activations