© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14708
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the very first substantive word of each new section or segment (i.e. paragraph- or topic-initial content words).

    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
     réfé
    0.61
    Datum
    0.59
    這裡是
    0.59
     прости
    0.59
    簡單
    0.58
    INSTDIR
    0.57
    ่าย
    0.56
    葡
    0.56
     cited
    0.55
    這裡
    0.55
    POSITIVE LOGITS
     автомобиль
    0.91
     खासा
    0.82
     posao
    0.72
    かれた
    0.71
     retribution
    0.71
    чкой
    0.70
     fars
    0.70
    henko
    0.69
     lento
    0.69
    +]
    0.67
    Activations Density 0.000%

    No Known Activations