© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54381
    Prev
    Next
    INDEX
    Explanations

    latex math symbols

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

    The neuron strongly activates on individual mathematical symbols or variable names (e.g. identifiers, Greek letters, subscripts) appearing inside LaTeX‐style math expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
    .*/
    -1.09
    stination
    -1.09
    Called
    -1.08
    Kesimpulan
    -1.07
     cambiare
    -1.07
     seyn
    -1.05
    /*!
    
    -1.05
    ecie
    -1.05
     giebt
    -1.03
     prophylactic
    -1.02
    POSITIVE LOGITS
     of
    2.89
     that
    2.11
     in
    1.67
     which
    1.62
     whose
    1.59
     who
    1.52
     from
    1.49
     for
    1.48
    taya
    1.23
    tya
    1.20
    Activations Density 0.037%

    No Known Activations