© 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. 11383
    Prev
    Next
    INDEX
    Explanations

    Class, Order, Family, Genus, Species

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

    The neuron selectively activates on decimal‐formatted numeric values (floating‐point measurements and statistics).

    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
    ف
    0.88
    َا
    0.82
    ة
    0.81
    ت
    0.79
    ing
    0.79
    پر
    0.73
    لا
    0.72
    ل
    0.71
     zufrieden
    0.71
     schermo
    0.69
    POSITIVE LOGITS
    ўнай
    1.00
     hydrazine
    0.86
     тока
    0.84
     нацыяна
    0.83
     свидетель
    0.83
     Такой
    0.83
     разработан
    0.82
    ўным
    0.82
     жил
    0.82
    ྫ
    0.80
    Activations Density 0.001%

    No Known Activations