© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70234
    Prev
    Next
    INDEX
    Explanations

    Hong Kong and related events

    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
    食堂
    -0.77
     pép
    -0.72
     padding
    -0.72
     vort
    -0.70
     infância
    -0.68
     feste
    -0.68
     Wax
    -0.68
     recessive
    -0.67
     rustic
    -0.67
     above
    -0.66
    POSITIVE LOGITS
     Hong
    1.86
    Hong
    1.52
     HK
    1.45
     Hongkong
    1.34
    HK
    1.27
     Causeway
    1.20
     hong
    1.09
     Umbrella
    1.07
     democracy
    1.02
    香港
    0.99
    Activations Density 0.007%

    No Known Activations