© 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. 22-GEMMASCOPE-RES-131K
    7. 127883
    Prev
    Next
    INDEX
    Explanations

    This neuron detects tokens belonging to mathematical formulas, especially LaTeX math notation (numbers, operators, and formatting commands).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    multi-lingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     Pilate
    -1.11
     vektor
    -1.05
    utzt
    -0.98
    みが
    -0.94
     Hydrogen
    -0.92
     Новости
    -0.91
     sql
    -0.91
    SqlParameter
    -0.91
    繳
    -0.90
     preferred
    -0.89
    POSITIVE LOGITS
     religieux
    0.89
    kespeare
    0.88
     byť
    0.86
     благода
    0.84
     Europäischen
    0.84
     τὰ
    0.83
     hábit
    0.82
     第
    0.82
    iornamento
    0.82
     whack
    0.81
    Activations Density 0.013%

    No Known Activations