© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1213
    Prev
    Next
    INDEX
    Explanations

    urls starting with https://

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

    This neuron identifies bibliographic and citation metadata markers (e.g., “Archived,” “Retrieved,” superscript arrows, dates, and archive URLs) in reference or footnote sections.

    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
     bores
    0.63
    Continue
    0.55
     takeaways
    0.52
    ...
    0.52
     benef
    0.51
    ोगी
    0.51
    嗡
    0.51
     Sunday
    0.50
     soh
    0.50
     मीटिंग
    0.50
    POSITIVE LOGITS
     Archived
    0.76
     {{{
    0.75
     Encyclopædia
    0.74
     Архиви
    0.71
     Diarsipkan
    0.70
     لە
    0.69
     Lexikon
    0.68
    ictionnaire
    0.67
     Сайт
    0.65
     Encyclopedia
    0.65
    Activations Density 0.010%

    No Known Activations