© 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. 15294
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (digits, numbers, dates, levels, phone numbers, etc.).

    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
     aspects
    0.82
     astring
    0.79
    是因为
    0.74
     arise
    0.73
    的原因
    0.72
    螈
    0.72
    гатьох
    0.72
    蓁
    0.71
     アクセサリー
    0.70
     arises
    0.70
    POSITIVE LOGITS
    ik
    0.71
    sufficient
    0.70
    ซึ่ง
    0.70
    less
    0.68
    which
    0.68
     conseguiu
    0.66
     cuja
    0.66
     والذي
    0.66
    andowski
    0.64
    которые
    0.64
    Activations Density 2.436%

    No Known Activations