© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14126
    Prev
    Next
    INDEX
    Explanations

    imported technology or database cursor

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

    The neuron activates on tokens representing decimal numeric values (floating-point numbers).

    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
    लिंग
    0.80
     răm
    0.79
     thế
    0.76
    sohn
    0.76
    rech
    0.73
    u
    0.73
     Erg
    0.70
    geht
    0.69
    hme
    0.68
    seiten
    0.68
    POSITIVE LOGITS
    ায়ার
    0.83
     他们
    0.79
     المنتخب
    0.73
    زوج
    0.73
    𝖾
    0.72
    ุณ
    0.71
    arnas
    0.71
    ў
    0.70
     雪
    0.69
     车
    0.69
    Activations Density 0.000%

    No Known Activations