© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    encoding to bytes

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

    The neuron is specialized to detect numeric tokens that include decimal points (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
    Sumber
    0.94
    ফটেন
    0.85
    餛
    0.83
     DISCOUNT
    0.79
    ið
    0.77
    żu
    0.75
    嵃
    0.74
     Questions
    0.73
     देण्यासाठी
    0.73
    搗
    0.72
    POSITIVE LOGITS
     сложности
    0.86
     большой
    0.84
     челове
    0.84
     состав
    0.82
     точки
    0.82
     Второй
    0.82
     производи
    0.80
     коллек
    0.80
     увидеть
    0.80
    имость
    0.78
    Activations Density 0.001%

    No Known Activations