© 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. 12741
    Prev
    Next
    INDEX
    Explanations

    visual learners

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

    The neuron is keyed to numerical data tokens—i.e. it lights up on numbers (metric values) 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
    פ
    0.85
    Ле
    0.73
    вести
    0.73
    charAt
    0.72
    억
    0.72
    вому
    0.71
    И
    0.71
    डी
    0.71
    바일
    0.70
    еру
    0.70
    POSITIVE LOGITS
     nächste
    0.75
    acija
    0.74
     คลิ
    0.73
     tahap
    0.73
     Vào
    0.71
    Closeup
    0.70
     เนื้อ
    0.69
     เธอ
    0.68
     ople
    0.68
     Echt
    0.68
    Activations Density 0.000%

    No Known Activations