© 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. 10705
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens, especially those used in citations or reference-style numbers (e.g., years, volume and page 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
    -
    0.68
    _
    0.68
     đồng
    0.65
     oleh
    0.64
    =
    0.63
     betreff
    0.60
    :
    0.60
    있
    0.60
     był
    0.59
    .{
    0.59
    POSITIVE LOGITS
     たり
    0.68
     ئى
    0.66
     grasslands
    0.65
    觉得自己
    0.64
    osław
    0.64
    стой
    0.63
     forêts
    0.63
     grits
    0.63
     biofuels
    0.62
    ów
    0.61
    Activations Density 5.892%

    No Known Activations