© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71404
    Prev
    Next
    INDEX
    Explanations

    id attribute in XML/code

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

    The neuron detects the syntax for named capture groups (i.e. the “(?<name>” constructs) in regular expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     both
    -1.68
     because
    -1.59
     during
    -1.59
    鮟
    -1.48
    蕯
    -1.42
     what
    -1.42
     when
    -1.42
    棪
    -1.41
    鹀
    -1.40
    (´
    -1.38
    POSITIVE LOGITS
    '
    2.33
     REALLY
    1.77
      
    1.55
     alluring
    1.53
    A
    1.52
    K
    1.48
    We
    1.47
     VERY
    1.46
     unbelievably
    1.45
    ur
    1.42
    Activations Density 0.001%

    No Known Activations