© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by tokens representing decimal numbers (floating‐point numeric strings).

    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
     खबरों
    0.67
    🏼
    0.66
     querem
    0.63
     Wählen
    0.62
    veratrol
    0.61
    entar
    0.61
     Sweater
    0.61
    なども
    0.59
     daug
    0.59
     መ
    0.58
    POSITIVE LOGITS
     istri
    1.00
     İyi
    0.92
     ilości
    0.87
     istilah
    0.86
     iklan
    0.85
     iyi
    0.84
     iş
    0.84
     имени
    0.83
     iria
    0.83
     istnie
    0.82
    Activations Density 1.708%

    No Known Activations