© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    manufacturing company

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

    The neuron fires on numeric quantities (measurements, counts, or other numbers) 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
    ar
    0.88
    ுள்ளனர்
    0.81
    oi
    0.80
    不够
    0.80
    为了
    0.79
    u
    0.78
    僖
    0.77
    ad
    0.75
    ل
    0.74
    al
    0.73
    POSITIVE LOGITS
     рода
    0.83
     полного
    0.81
     primeira
    0.80
     sinais
    0.79
     siêu
    0.79
    +][
    0.76
     primeiros
    0.75
     перио
    0.74
     escolas
    0.74
     показывать
    0.74
    Activations Density 0.000%

    No Known Activations