© 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. 6792
    Prev
    Next
    INDEX
    Explanations

    Protected Health Information

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

    The neuron fires on domain‐specific or technical jargon—words like “apothecary,” “psychotherapy,” “color-treated,” “connection,” etc.

    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
     سرعت
    0.75
    我已经
    0.73
    某一
    0.73
    再一次
    0.70
     পরবর্তীতে
    0.70
    工事
    0.68
    或者是
    0.68
    非常に
    0.67
    予想
    0.67
    Adidas
    0.67
    POSITIVE LOGITS
     and
    0.79
    ."
    0.75
    .
    0.72
    .&
    0.70
    !
    0.66
     svoj
    0.66
     convivial
    0.65
     &
    0.64
    .]
    0.63
     privacy
    0.63
    Activations Density 0.150%

    No Known Activations