© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6899
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on tokens that are part of numerical expressions—dates, times, quantities, and other number‐related references.

    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
    arket
    0.89
     diseñada
    0.82
    可以
    0.81
    Lx
    0.81
    nál
    0.79
    arbe
    0.78
     efficace
    0.78
    奚
    0.76
    입니다
    0.75
    də
    0.75
    POSITIVE LOGITS
     đảo
    0.69
     Ген
    0.68
     sailboats
    0.63
    becue
    0.61
    燁
    0.61
     до
    0.61
     Chat
    0.61
     bakt
    0.61
     tới
    0.60
     Chats
    0.59
    Activations Density 0.000%

    No Known Activations