© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40019
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and symbols

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

    The neuron flags bits of mathematical notation—numbers, operators (like =, +, *), and function names (e.g. cos, sin)—within formulas.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    one
    -0.89
    than
    -0.84
     feature
    -0.82
    ticker
    -0.79
    then
    -0.79
    order
    -0.79
     Feature
    -0.78
    をご
    -0.77
    rought
    -0.77
     target
    -0.77
    POSITIVE LOGITS
    fieldId
    0.91
    πομπ
    0.89
     baloncesto
    0.87
     kemajuan
    0.82
     jejich
    0.82
     návště
    0.82
     accompagné
    0.81
     zowel
    0.80
     hochwertige
    0.80
     både
    0.79
    Activations Density 0.062%

    No Known Activations