© 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. 127772
    Prev
    Next
    INDEX
    Explanations

    The neuron is tuned to spot LaTeX‐style mathematical notation (math‐mode symbols, commands, and formula tokens).

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

    mathematical/code syntax (`$`, `\`, `mathbb`, `lim`, `=`, `i.e.`, `List<>`, `(`, `A`)

    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
     финан
    -0.94
    osof
    -0.85
     ck
    -0.83
    ूत
    -0.81
    เลือก
    -0.80
    Ꭻ
    -0.79
    inars
    -0.79
     Vorbereitung
    -0.77
    も同じ
    -0.77
     vorsichtig
    -0.77
    POSITIVE LOGITS
     like
    0.97
     kérd
    0.90
     really
    0.89
     $\
    0.88
    詔
    0.87
     например
    0.85
    >=</
    0.85
     new
    0.84
     např
    0.84
    After
    0.83
    Activations Density 0.077%

    No Known Activations