© 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. 34-GEMMASCOPE-RES-131K
    7. 57332
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and inequalities

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

    This neuron detects LaTeX‐style mathematical expressions (e.g. fractions, exponents, inequality symbols, and function names like “sqrt”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     only
    -1.64
     ONLY
    -1.09
     also
    -1.08
     undoubtedly
    -1.07
     mostly
    -1.07
     at
    -1.06
     although
    -1.05
     presumably
    -1.05
     even
    -1.02
     because
    -1.02
    POSITIVE LOGITS
     zoude
    1.28
    
    1.27
    
    1.24
     Dinas
    1.18
    гато
    1.17
    zzet
    1.15
    alogical
    1.15
     スリーブ
    1.13
    ඍ
    1.13
    ologische
    1.12
    Activations Density 0.028%

    No Known Activations