© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31341
    Prev
    Next
    INDEX
    Explanations

    Beijing and Peking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dolor
    -0.81
     Sindh
    -0.81
     Sarawak
    -0.79
     Jalisco
    -0.75
    padek
    -0.75
     père
    -0.74
    щений
    -0.73
    📀
    -0.73
    タオル
    -0.73
    TAT
    -0.72
    POSITIVE LOGITS
     Beijing
    1.75
    Beijing
    1.59
     Canberra
    1.23
     北京
    1.22
    北京
    1.18
     Delhi
    1.17
     Peking
    1.12
     Ottawa
    1.09
     दिल्ली
    1.06
    Ottawa
    1.05
    Activations Density 0.014%

    No Known Activations