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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85845
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and equations

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

    This neuron fires on tokens that are part of mathematical formulae (LaTeX‐style math), such as variable names, Greek letters, operators, and matrix commands.

    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
     even
    -3.27
     will
    -2.98
     all
    -2.97
     with
    -2.94
     this
    -2.80
     both
    -2.77
     it
    -2.56
     on
    -2.52
     three
    -2.48
     also
    -2.45
    POSITIVE LOGITS
    鳚
    2.19
    GRACIAS
    2.00
     vaste
    1.98
     serre
    1.98
     geene
    1.94
     offerte
    1.92
    HISTORIA
    1.92
     étan
    1.91
    usually
    1.91
     lumine
    1.91
    Activations Density 0.324%

    No Known Activations