© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    details or instructions

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

    The neuron strongly activates on numeric specifications—numbers, measurements, dates, and other quantitative tokens.

    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
    喩
    0.80
     EPFO
    0.68
     TRPV
    0.68
     NEP
    0.68
    ссы
    0.67
    ঘাতে
    0.67
    Пи
    0.65
     hedgehog
    0.64
    РЕ
    0.63
    гли
    0.63
    POSITIVE LOGITS
    {
    0.93
     lainnya
    0.82
     yağ
    0.80
     anschließend
    0.80
     peau
    0.79
     Wooden
    0.79
     kezd
    0.77
     Days
    0.77
     settimane
    0.76
    ী
    0.76
    Activations Density 0.000%

    No Known Activations