© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2910
    Prev
    Next
    INDEX
    Explanations

    Chinese provinces and cities

    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_40_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
    鲔
    0.82
    皞
    0.80
    潾
    0.77
    贰百
    0.76
    蓣
    0.75
    诹
    0.75
    璈
    0.75
    澼
    0.75
    嵃
    0.74
    珽
    0.74
    POSITIVE LOGITS
     Beijing
    1.19
     Jiangsu
    1.18
     Zhejiang
    1.17
     Shanghai
    1.13
     Guangdong
    1.08
     Nanjing
    1.07
     Xinjiang
    1.05
     Shandong
    1.04
     Chongqing
    1.04
     provincial
    1.03
    Activations Density 0.142%

    No Known Activations