© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102253
    Prev
    Next
    INDEX
    Explanations

    regex search and match

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

    regex pattern matching operations, particularly invocations of pattern matching functions like `preg_match`, `match`, `search`, and regex operators like `=~`.

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

    The neuron fires on regex‐related function or method calls (e.g. “search,” “match,” “findall”) 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_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
     pintores
    -1.55
     никаких
    -1.51
    与其
    -1.44
     ثلاثة
    -1.43
     edificios
    -1.42
    一个小
    -1.42
     sonidos
    -1.41
    ing
    -1.41
    爱心
    -1.39
     "
    -1.38
    POSITIVE LOGITS
     that
    1.68
     this
    1.62
    Toponymie
    1.58
     the
    1.53
     then
    1.48
     all
    1.41
     your
    1.40
    Dalam
    1.37
     of
    1.35
     each
    1.34
    Activations Density 0.005%

    No Known Activations