© 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. 22-GEMMASCOPE-RES-131K
    7. 16634
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals

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

    This neuron detects mathematical notation—especially LaTeX-style integral signs, coordinate symbols, and related formula tokens.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     quick
    -1.26
     his
    -1.20
     DELHI
    -1.20
     him
    -1.20
     گوشی
    -1.15
    GenerationType
    -1.13
    ::$_
    -1.12
     process
    -1.09
     arrested
    -1.09
    ֔
    -1.07
    POSITIVE LOGITS
    崛
    1.25
    æde
    1.14
     プリント
    1.13
    viamo
    1.13
     questões
    1.08
     geralmente
    1.07
     EoL
    1.06
     huu
    1.06
    シス
    1.05
     ܝ
    1.05
    Activations Density 0.034%

    No Known Activations