© 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. 16203
    Prev
    Next
    INDEX
    Explanations

    among the top

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

    The neuron is tuned to detect numeric tokens—quantities, measurements, decimal values, citations, and the like.

    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
    رخ
    0.96
    然後
    0.90
     annan
    0.86
    然后
    0.81
     imparted
    0.79
    পূ
    0.77
    हमारे
    0.76
    ;"+
    0.75
     ㅇ
    0.73
    啈
    0.73
    POSITIVE LOGITS
     maand
    0.79
    gericht
    0.75
    HO
    0.74
    ски
    0.71
     ভেসে
    0.71
    RON
    0.70
    ഴി
    0.70
    GET
    0.70
    ীয়
    0.68
    ях
    0.67
    Activations Density 0.000%

    No Known Activations