© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4155
    Prev
    Next
    INDEX
    Explanations

    said, stated, recounted, exclaimed

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

    The neuron strongly activates on the markers of reported speech—quotation boundaries and the verbs that attribute statements—identifying where someone is being quoted or cited.

    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
    ;:
    0.66
    ;
    0.63
    ":
    0.59
    daki
    0.59
    や
    0.57
     growing
    0.55
    についての
    0.54
     (=
    0.54
    
    0.54
     conjunction
    0.53
    POSITIVE LOGITS
     कच्छ
    0.78
     こちら
    0.77
     இவ்வாறு
    0.75
     фаразы
    0.75
     initialise
    0.75
    ॕ
    0.72
    initial
    0.71
     indicó
    0.71
     Recordemos
    0.71
     создал
    0.70
    Activations Density 0.014%

    No Known Activations