© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73025
    Prev
    Next
    INDEX
    Explanations

    math formulas and variables

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

    This neuron detects variable symbols (like single‐letter variables or Greek letters) inside mathematical/LaTeX 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
     только
    -1.13
     \%,
    -1.01
     این
    -0.99
     only
    -0.97
     vinagre
    -0.97
    terrasse
    -0.95
    İK
    -0.93
    BRL
    -0.93
    BNL
    -0.90
    bilde
    -0.90
    POSITIVE LOGITS
    like
    0.96
    y
    0.91
     like
    0.91
    requ
    0.91
    twice
    0.90
     häufiger
    0.90
    particularly
    0.87
    dep
    0.86
     Veranstaltungen
    0.86
    想想
    0.85
    Activations Density 0.014%

    No Known Activations