© 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. 10-GEMMASCOPE-RES-131K
    7. 7716
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

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

    The neuron detects numeric and mathematical tokens—especially numbers, variables, and symbols—within formulas and equations.

    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
    }$
    -1.98
    冬の
    -1.97
    e
    -1.73
    %;
    -1.71
    洶
    -1.64
     bewertet
    -1.63
    ть
    -1.62
     доволь
    -1.61
     vermel
    -1.59
     beraten
    -1.56
    POSITIVE LOGITS
     ถ้า
    2.03
    '
    1.85
     ผม
    1.73
    getNome
    1.61
     they
    1.61
     is
    1.55
    と呼ばれる
    1.52
     was
    1.51
     If
    1.50
     Wenn
    1.48
    Activations Density 0.038%

    No Known Activations