© 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. 79518
    Prev
    Next
    INDEX
    Explanations

    special characters and separators

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

    This neuron detects words naming or describing punctuation and other special characters (e.g. “hash,” “comma,” “quotes,” “slash,” etc.).

    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
     schop
    -0.81
    思议
    -0.79
    fluor
    -0.79
    siapkan
    -0.79
    beschreibung
    -0.78
    illés
    -0.77
     Ayrıca
    -0.75
     with
    -0.75
     consisting
    -0.75
    ONIC
    -0.74
    POSITIVE LOGITS
     marks
    1.27
     character
    1.16
     sign
    1.16
     mark
    1.09
     symbol
    1.08
    Neue
    0.97
     signs
    0.94
     framför
    0.88
     characters
    0.82
     operator
    0.80
    Activations Density 0.112%

    No Known Activations