© 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. 15292
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens (numbers or numerical data) 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_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
    至於
    0.88
     моей
    0.86
    Ā
    0.85
    Ы
    0.84
    Ꮟ
    0.84
     negó
    0.81
    ให้กับ
    0.81
    экономи
    0.80
    ﺸ
    0.80
    ги
    0.79
    POSITIVE LOGITS
     Chess
    0.75
    t
    0.70
     pò
    0.68
    tre
    0.67
     வேண்ட
    0.67
     intrepid
    0.66
     printr
    0.66
    opra
    0.65
    铌
    0.64
     NG
    0.64
    Activations Density 0.000%

    No Known Activations