© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7491
    Prev
    Next
    INDEX
    Explanations

    manufacturing and China

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    愆
    0.64
     décès
    0.60
    ўцаў
    0.60
     śmierci
    0.60
    慝
    0.59
     otáz
    0.59
    󠁣
    0.59
     教え
    0.58
    㑒
    0.58
     traged
    0.57
    POSITIVE LOGITS
     Guangzhou
    1.00
     Shandong
    0.95
     Chengdu
    0.91
     factory
    0.90
     Shenzhen
    0.89
     Jiangsu
    0.87
     customized
    0.83
     China
    0.80
     Hangzhou
    0.80
     Guangdong
    0.79
    Activations Density 0.010%

    No Known Activations