© 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. 10-GEMMASCOPE-RES-131K
    7. 103154
    Prev
    Next
    INDEX
    Explanations

    special characters in patterns

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

    footnote or reference markers in academic and technical documents.

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

    The neuron activates on regular‐expression syntax—especially the caret‐anchor “^” and the “[ˆ…]” negated‐character‐class patterns.

    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
     But
    -3.56
    8
    -2.92
    1
    -2.92
    ar
    -2.61
    ↵
    -2.53
    u
    -2.53
     This
    -2.50
    {"
    -2.48
    x
    -2.48
     Resultat
    -2.44
    POSITIVE LOGITS
    AutoresizingMask
    2.72
    扪
    2.20
     donnent
    2.20
     trouvent
    2.19
     ferait
    2.13
     sparkle
    2.09
    榈
    2.09
    тися
    2.09
    ﻥ
    2.08
    varlak
    2.06
    Activations Density 0.010%

    No Known Activations