© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    countries and institutions

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

    The neuron is primarily triggered by numerical tokens—especially floating-point numbers or measurements embedded 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
    !
    0.82
     our
    0.77
    ’;
    0.77
     we
    0.76
    ?
    0.75
    ！
    0.73
     regs
    0.73
    ’!
    0.72
    ’.
    0.71
     nossa
    0.71
    POSITIVE LOGITS
     "[
    0.76
     कथित
    0.72
     /ˈ
    0.71
    ),[
    0.70
     Также
    0.68
    截至
    0.68
     يُ
    0.67
     Diarsipkan
    0.67
    ڊ
    0.67
    ٬
    0.67
    Activations Density 0.001%

    No Known Activations