© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens—especially standalone numbers or numeric identifiers (e.g. floats, publication IDs, DOIs) 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
    льзу
    0.87
    enen
    0.86
    icletas
    0.79
     использовать
    0.74
     शस्त्र
    0.74
    웍
    0.73
    ersch
    0.73
    lery
    0.72
    ennie
    0.71
    ennies
    0.71
    POSITIVE LOGITS
    مح
    0.83
    捶
    0.76
    Ｐ
    0.75
    电
    0.75
     INFIN
    0.72
    实现
    0.71
    秦
    0.71
    补充
    0.71
    瞻
    0.70
    鞅
    0.70
    Activations Density 0.000%

    No Known Activations