© 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. 10-GEMMASCOPE-RES-131K
    7. 68601
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formulas

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

    This neuron fires on LaTeX math‐mode commands and equation‐formatting tokens (e.g. align, numbered equations, mbox, Δ, backslash commands) in the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -1.81
     vardı
    -1.52
     who
    -1.47
     one
    -1.47
     explicar
    -1.42
     memenangkan
    -1.39
     гостиной
    -1.35
     znaczy
    -1.34
     offizi
    -1.33
     unul
    -1.32
    POSITIVE LOGITS
     it
    1.55
    when
    1.48
     is
    1.48
     cruda
    1.45
     می‌
    1.44
     român
    1.43
     fria
    1.40
     restant
    1.40
    謌
    1.39
     censura
    1.38
    Activations Density 0.019%

    No Known Activations