© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    contextual emphasis

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (e.g. digits, years, page or section numbers) wherever they appear 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
     noite
    0.77
    पीय
    0.77
     descuentos
    0.75
    㐄
    0.75
    สิ้น
    0.74
     discounts
    0.72
    点セット
    0.71
     conquests
    0.71
    নিবেশ
    0.70
     aritmética
    0.70
    POSITIVE LOGITS
     Tz
    0.73
    ід
    0.72
     उसे
    0.72
     Hew
    0.71
     Hive
    0.71
    (
    0.71
    ivă
    0.70
     kemudian
    0.70
     możli
    0.70
    asan
    0.70
    Activations Density 0.000%

    No Known Activations