© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13855
    Prev
    Next
    INDEX
    Explanations

    Chinese place names and regions

    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
    螫
    0.76
    螓
    0.72
    鲷
    0.71
    蓍
    0.70
    鐒
    0.70
    颶
    0.70
    鳕
    0.69
    皞
    0.69
    溽
    0.69
     അമേരിക്ക
    0.68
    POSITIVE LOGITS
     Chinese
    1.02
     Beijing
    1.01
     Shanghai
    0.92
     chinese
    0.88
     Chongqing
    0.87
     Sichuan
    0.86
     Peking
    0.80
     China
    0.79
     Guangdong
    0.78
    Beijing
    0.77
    Activations Density 0.106%

    No Known Activations