© 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. 98329
    Prev
    Next
    INDEX
    Explanations

    polynomial expressions

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

    This neuron detects numeric and arithmetic-expression tokens (numbers, variables, and operators) in mathematical 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
    وشی
    -1.10
    Ār
    -1.00
    ggable
    -0.97
     ffilm
    -0.97
     botones
    -0.96
    ativen
    -0.96
     menyal
    -0.96
     Новости
    -0.95
     extenso
    -0.94
     processos
    -0.93
    POSITIVE LOGITS
     vielmehr
    0.96
     note
    0.90
     contribuye
    0.90
     Vortrag
    0.88
     später
    0.87
    いましたが
    0.87
     brought
    0.85
     today
    0.85
    icer
    0.85
     rural
    0.84
    Activations Density 0.013%

    No Known Activations