© 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. 10138
    Prev
    Next
    INDEX
    Explanations

    filler list

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

    The neuron is specialized to detect mentions of tangible materials or substances (e.g., cotton, silk, helium, gas).

    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
     wagg
    0.68
     цена
    0.66
    鹘
    0.66
     ಯಾವುದೇ
    0.64
     можна
    0.62
     그냥
    0.62
     marchandises
    0.62
    是没有
    0.62
     china
    0.61
     tariff
    0.61
    POSITIVE LOGITS
    들과
    0.83
    ric
    0.73
    p
    0.73
    များနှင့်
    0.71
     and
    0.70
    v
    0.70
    Cardiac
    0.69
    ‌های
    0.69
    ികളും
    0.69
    d
    0.68
    Activations Density 2.636%

    No Known Activations