© 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. 10-GEMMASCOPE-RES-131K
    7. 48217
    Prev
    Next
    INDEX
    Explanations

    RegExp

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

    The neuron consistently fires on occurrences of “RegExp” or “regexp” (i.e. explicit references to regular‐expression objects or patterns in code).

    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
    This
    -3.28
    It
    -2.91
    Of
    -2.83
    Another
    -2.70
     για
    -2.67
    蘩
    -2.66
    They
    -2.64
    妡
    -2.61
     ‘
    -2.61
    There
    -2.59
    POSITIVE LOGITS
    柺
    2.61
    燊
    2.42
     från
    2.34
    畚
    2.30
     ktorý
    2.27
    呔
    2.25
    栴
    2.22
     şi
    2.19
     冊
    2.17
    蚺
    2.17
    Activations Density 0.001%

    No Known Activations