© 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. 517
    Prev
    Next
    INDEX
    Explanations

    quoted dialogue attribution

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

    This neuron detects the start of a direct quotation (the opening quote and its initial word).

    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
     あなた
    0.86
     YOUR
    0.80
     ನಿಮ್ಮ
    0.79
     Puedes
    0.77
     Taehyung
    0.76
     乀
    0.75
     İşte
    0.75
     Однако
    0.75
     Jungkook
    0.75
     Согласно
    0.75
    POSITIVE LOGITS
     [
    0.89
    [
    0.67
    ;
    0.66
     data
    0.65
     strata
    0.63
    :
    0.62
     spectrum
    0.61
     in
    0.61
     versus
    0.61
     tonnage
    0.61
    Activations Density 0.046%

    No Known Activations