© 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. 7436
    Prev
    Next
    INDEX
    Explanations

    introductions and clarifications

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

    This neuron fires most strongly on numerical data or statistics (dates, quantities, percentages, identification numbers) in the text.

    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
     évidence
    0.57
    ęć
    0.52
     appliqu
    0.51
    ➊
    0.51
    ählen
    0.51
    minLength
    0.50
    électricité
    0.49
    arguments
    0.49
    opacity
    0.49
     sto
    0.48
    POSITIVE LOGITS
    据悉
    0.77
     据
    0.77
     Meanwhile
    0.75
     SOURCE
    0.74
     Details
    0.73
    ៕
    0.72
     Interested
    0.71
    한편
    0.70
    Meanwhile
    0.68
     Additional
    0.67
    Activations Density 0.181%

    No Known Activations