© 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. 6104
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on specialized technical or domain-specific terms and jargon (e.g. engineering, scientific, legal, or professional vocabulary).

    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
    江苏
    0.91
    剿
    0.90
    出了
    0.87
    基础
    0.87
    龙
    0.86
    影响
    0.86
    陈
    0.86
    太空
    0.84
    显
    0.84
    罗
    0.84
    POSITIVE LOGITS
     일본
    1.41
     ※
    1.38
     Osaka
    1.37
     Fukuoka
    1.37
     japonés
    1.33
     Japón
    1.30
     JAPAN
    1.23
     Giappone
    1.22
     sashimi
    1.21
     Hokkaido
    1.20
    Activations Density 0.603%

    No Known Activations