© 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. 10580
    Prev
    Next
    INDEX
    Explanations

    majority Russian population

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

    The neuron strongly activates on comma tokens, effectively detecting commas 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
    ut
    0.81
    d
    0.80
    대의
    0.76
    ك
    0.73
    hesion
    0.73
    dni
    0.73
     قائ
    0.72
    TMS
    0.72
    є
    0.72
    reverse
    0.71
    POSITIVE LOGITS
     mucous
    0.84
     ghế
    0.83
     smel
    0.82
     reptiles
    0.82
     scars
    0.80
    エイ
    0.78
     creeps
    0.77
     zippers
    0.77
     clerks
    0.77
    ঞ্জ
    0.76
    Activations Density 0.001%

    No Known Activations