© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8400
    Prev
    Next
    INDEX
    Explanations

    keys, values, four, one

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

    The neuron is strongly activated by terms associated with online commerce transactions—words like “online,” payment actions (“deposit,” “pay,” “shipment”), product/brand names, and calls to buy.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ર્ડ
    0.78
     star
    0.74
     brook
    0.73
     transaction
    0.72
     bee
    0.72
    াচিত
    0.71
     advisers
    0.71
     rho
    0.71
     hawks
    0.70
    ್‌
    0.70
    POSITIVE LOGITS
    tfidf
    0.79
    ßen
    0.79
    으로써
    0.76
    지난
    0.76
     ограни
    0.75
    Monkey
    0.75
    вете
    0.73
     наверное
    0.73
    적인
    0.71
    連続
    0.71
    Activations Density 0.000%

    No Known Activations