© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1291
    Prev
    Next
    INDEX
    Explanations

    Chinese cities and business

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

    China and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    鲔
    1.13
    拁
    1.07
    鳃
    1.01
    螓
    1.01
    螫
    1.01
    玧
    1.01
    柽
    1.00
    鳕
    0.99
    睪
    0.98
    銠
    0.97
    POSITIVE LOGITS
     Beijing
    1.54
     Chinese
    1.40
     Chongqing
    1.34
     Shanghai
    1.33
     China
    1.27
     Nanjing
    1.25
     chinese
    1.24
     Chengdu
    1.23
     Guangzhou
    1.21
     Sichuan
    1.21
    Activations Density 0.181%

    No Known Activations