© 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. 34-GEMMASCOPE-RES-131K
    4. 75591
    Prev
    Next
    INDEX
    Explanations

    regex special characters

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

    The neuron fires on regular‐expression syntax—particularly the slash‐delimited pattern, quantifier numbers, and flags like “g.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -0.97
     as
    -0.87
     to
    -0.84
     of
    -0.84
     ل
    -0.82
     along
    -0.81
     for
    -0.80
    what
    -0.77
    Band
    -0.75
     エンタメ
    -0.75
    POSITIVE LOGITS
    gi
    1.06
    gm
    1.05
     électron
    0.97
    ventes
    0.94
    alucía
    0.93
    romeda
    0.89
    iamo
    0.87
    termilk
    0.85
     opérateur
    0.85
    グロー
    0.84
    Activations Density 0.014%

    No Known Activations