© 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. 11063
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the first content word of each new text segment, effectively marking the start of a new document or paragraph.

    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
     religiosas
    0.64
     امرأة
    0.64
    bpy
    0.64
    ના
    0.63
    ot
    0.62
     брат
    0.60
    gericht
    0.59
    鄙
    0.59
    klar
    0.58
    orte
    0.58
    POSITIVE LOGITS
    峎
    0.86
     アクセ
    0.81
     saddhim
    0.77
    うまく
    0.77
    十分
    0.77
     amplitud
    0.77
     rupam
    0.76
     happenings
    0.75
     trafi
    0.75
     affording
    0.75
    Activations Density 0.038%

    No Known Activations