© 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. 34-GEMMASCOPE-RES-131K
    7. 56698
    Prev
    Next
    INDEX
    Explanations

    regex operations and preg_match

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

    The neuron activates on mentions of regex library calls or function names (e.g. preg_match, Regex.Split, regexp.MustCompile).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pensamento
    -0.80
    Promote
    -0.79
     jouant
    -0.76
     morals
    -0.76
    accom
    -0.75
    Genes
    -0.74
    Watts
    -0.73
     рынке
    -0.72
    benefits
    -0.71
    fptr
    -0.71
    POSITIVE LOGITS
    replace
    1.12
     replace
    0.89
     replacement
    0.85
     replacing
    0.84
    match
    0.81
     Replace
    0.81
    SUPPORTED
    0.77
    景點
    0.77
     replacements
    0.76
     Denison
    0.76
    Activations Density 0.004%

    No Known Activations