© 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. 25807
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with symbols

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

    This neuron detects tokens that are part of mathematical notation (LaTeX or math‐mode symbols, operators, and relations).

    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
    asants
    -1.41
     myös
    -1.35
     alcune
    -1.28
     contém
    -1.27
     oferece
    -1.27
    และ
    -1.27
     realizó
    -1.25
     recibiendo
    -1.25
     recomendo
    -1.25
    ,;
    -1.23
    POSITIVE LOGITS
     because
    1.21
     ]:
    1.16
    😲
    1.09
    出来て
    1.09
     extenso
    1.09
     expertly
    1.08
    ньому
    1.07
     ४
    1.07
    bicara
    1.05
     exquisitely
    1.05
    Activations Density 0.064%

    No Known Activations