© 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. 7334
    Prev
    Next
    INDEX
    Explanations

    focus, invert, broader

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

    The neuron is primarily detecting numerical information—mentions of numbers, measurements, times, counts, and other quantitative data.

    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
    ↵↵
    0.72
    .
    0.70
    ;
    0.70
    ,
    0.67
    General
    0.64
    Group
    0.61
    J
    0.61
    M
    0.60
    B
    0.60
    Route
    0.59
    POSITIVE LOGITS
     disminución
    0.80
     २०२२
    0.79
     🥰
    0.73
     моей
    0.72
     alltid
    0.72
     andando
    0.72
     metaverse
    0.71
    🫶
    0.71
     covid
    0.71
     моего
    0.71
    Activations Density 0.611%

    No Known Activations