© 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. 58364
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

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

    This neuron flags tokens belonging to LaTeX‐style mathematical expressions—especially parentheses, braces, subscripts, and related symbols around variables (e.g. “(X_t)_ {…}”, “\_”, “$”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -1.56
    ing
    -1.41
     dizendo
    -1.28
     ficando
    -1.27
    ↵
    -1.27
     they
    -1.25
    groups
    -1.24
     was
    -1.23
    or
    -1.23
     podremos
    -1.22
    POSITIVE LOGITS
     {
    1.61
     preocupaciones
    1.54
     jätte
    1.52
     costumbres
    1.49
    Достоинства
    1.49
    咘
    1.48
    嘡
    1.48
    CÓ
    1.48
    Отлич
    1.45
    ۔
    1.44
    Activations Density 0.020%

    No Known Activations