© 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. 13995
    Prev
    Next
    INDEX
    Explanations

    types of structures

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

    The neuron primarily detects floating‐point numeric tokens (decimal 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
    ان
    0.84
    ق
    0.77
    ри
    0.73
    اا
    0.71
     معروف
    0.66
     الشع
    0.66
    ーション
    0.66
    imt
    0.66
    ビネット
    0.65
     प्रसिद्ध
    0.65
    POSITIVE LOGITS
     implementations
    0.70
     მაგრამ
    0.69
     albeit
    0.68
     când
    0.66
    基于
    0.65
     insofar
    0.65
     bốn
    0.64
    ﺱ
    0.64
     mutta
    0.63
     blistering
    0.63
    Activations Density 0.094%

    No Known Activations