© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    Siglo, Belle, contingency, direct, vehicles, prob, young, short, menc, gallery

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

    The neuron fires strongly on the first substantive word of a new paragraph or section (e.g. titles or topic-introducing nouns).

    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
    เหมาะสม
    0.52
    สิ่งที่
    0.50
    কেই
    0.50
    เป็นการ
    0.49
    เกี่ยวข้อง
    0.49
    விட்டால்
    0.49
    ใช้งาน
    0.47
    適切な
    0.47
    ()],
    0.47
     currentValue
    0.46
    POSITIVE LOGITS
     військо
    0.81
     چهار
    0.78
     трех
    0.78
     थाना
    0.77
     dvou
    0.77
     четырех
    0.74
     पांच
    0.73
     двух
    0.73
     छह
    0.73
     आठ
    0.72
    Activations Density 0.000%

    No Known Activations