© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99880
    Prev
    Next
    INDEX
    Explanations

    integral partition

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

    The neuron is specialized to pick out LaTeX‐style mathematical notation (especially integral symbols, subscripts, delimiters, and relational operators).

    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
     (%)
    -0.77
     Erm
    -0.71
    保護
    -0.71
     possessive
    -0.70
    rootScope
    -0.69
    disclosure
    -0.69
    czuk
    -0.67
    뚫
    -0.67
    トライ
    -0.67
     Бере
    -0.66
    POSITIVE LOGITS
     partition
    1.34
    partition
    1.02
    Partition
    0.97
     partitions
    0.88
    分割
    0.87
     Riemann
    0.85
     Partition
    0.80
    rectangle
    0.79
     Jump
    0.77
     sample
    0.76
    Activations Density 0.034%

    No Known Activations