© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15287
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially floating‐point or decimal numbers.

    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_24_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
     місце
    0.89
     травня
    0.86
     групи
    0.80
    +".
    0.75
    enapi
    0.75
     періо
    0.75
     розмі
    0.74
     повідом
    0.74
    muslim
    0.73
    {"
    0.72
    POSITIVE LOGITS
    ды
    0.99
     Utilize
    0.89
    стные
    0.85
    стная
    0.85
    лы
    0.84
     использование
    0.84
     использования
    0.83
     Использу
    0.82
    ্সে
    0.82
    ET
    0.81
    Activations Density 0.000%

    No Known Activations