© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10638
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens written as decimal numbers (i.e. floating-point literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    T
    1.13
    टी
    0.92
    ف
    0.82
    B
    0.79
    最
    0.79
    U
    0.77
    एक
    0.77
    交換
    0.75
    它
    0.75
    G
    0.74
    POSITIVE LOGITS
     richly
    0.75
     chrono
    0.73
     timeline
    0.72
     delay
    0.70
     ";
    0.70
     aftermath
    0.70
     unorthodox
    0.70
     ([[
    0.70
     chron
    0.70
     reinvigor
    0.70
    Activations Density 0.000%

    No Known Activations