© 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. 30009
    Prev
    Next
    INDEX
    Explanations

    special characters and programming syntax

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

    The neuron strongly activates on tokens with non-ordinary characters or formatting—e.g. uppercase or non-ASCII letters, XML tag names, comment-border symbols—i.e. any token containing unusual capitalization, punctuation, or extended characters.

    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
     nouveau
    -1.00
     Rheinland
    -0.94
     Khmer
    -0.82
    ордина
    -0.82
    猫咪
    -0.80
     COMPOUNDS
    -0.80
     Nuevo
    -0.77
     fjor
    -0.77
     traktor
    -0.76
    Lynch
    -0.75
    POSITIVE LOGITS
     против
    0.93
     სა
    0.91
     cơ
    0.88
     đáng
    0.88
    心配
    0.84
     nguy
    0.84
     Fassung
    0.84
     entschieden
    0.81
     trzyma
    0.81
     meio
    0.79
    Activations Density 0.007%

    No Known Activations