© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6354
    Prev
    Next
    INDEX
    Explanations

    p-groups or n-th

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

    The neuron activates on isolated single-letter mathematical variables (like p, k, or n) used in formulae or parameter definitions.

    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
     four
    0.79
     International
    0.69
     "/
    0.68
     Williamson
    0.66
     Trademark
    0.66
    avond
    0.66
     {
    0.65
    ">
    0.65
     ."
    0.64
     Ian
    0.64
    POSITIVE LOGITS
    ំពោះ
    0.84
     каждом
    0.71
    льными
    0.70
     следу
    0.70
     посмотрим
    0.69
     fehlen
    0.69
     каждая
    0.68
     чтения
    0.67
     планы
    0.66
     смотреть
    0.65
    Activations Density 0.001%

    No Known Activations