© 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. 58275
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

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

    The neuron is specialized to detect LaTeX‐style mathematical notation (dollar signs, backslashes, and math 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
     a
    -2.72
     the
    -2.17
    re
    -1.74
    á
    -1.63
    </h1>
    -1.53
    t
    -1.53
     they
    -1.49
     upto
    -1.47
    、
    -1.41
    ,
    -1.40
    POSITIVE LOGITS
     этого
    2.02
     estos
    2.00
     этих
    1.78
    ichtete
    1.73
     cuyos
    1.70
    ummings
    1.70
    ixeira
    1.70
     ľudí
    1.69
     tohoto
    1.69
     svoje
    1.69
    Activations Density 0.016%

    No Known Activations