© 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. 10-GEMMASCOPE-RES-131K
    7. 19461
    Prev
    Next
    INDEX
    Explanations

    numbers and surrounding words

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

    The neuron consistently activates on numeric tokens—especially numbers and decimal measurements—throughout the text.

    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
    ২
    -1.54
     Reſ
    -1.52
    прият
    -1.52
    mathrm
    -1.50
     Inſ
    -1.49
     algunas
    -1.48
    struzioni
    -1.41
     tampaknya
    -1.41
     Anſ
    -1.40
     zostanie
    -1.39
    POSITIVE LOGITS
     \&
    1.68
    ਖ਼
    1.46
     of
    1.33
     „
    1.31
    sukienka
    1.27
    #-
    1.21
    #(
    1.21
    
    1.19
     चीज़
    1.19
     ...)
    1.18
    Activations Density 1.012%

    No Known Activations