© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10792
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on numeric tokens—specifically floating‐point or decimal numbers in the text.

    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
    様々な
    0.70
     reac
    0.70
    ਗ
    0.68
    এক
    0.63
     парла
    0.63
    取付
    0.63
     enjeux
    0.63
    FEN
    0.62
    bindingFields
    0.62
    naming
    0.61
    POSITIVE LOGITS
    apabb
    0.73
     Hàm
    0.73
    ą
    0.72
     превы
    0.71
    iu
    0.71
    ﺂ
    0.71
     speł
    0.70
    ić
    0.70
     زيادة
    0.70
    utral
    0.70
    Activations Density 0.000%

    No Known Activations