© 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. 64191
    Prev
    Next
    INDEX
    Explanations

    Wuhan virus and locations

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

    geographic locations, particularly cities like Wuhan, and references to outbreaks or diseases.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     seaweed
    -0.80
    jā
    -0.78
     ов
    -0.77
    荼
    -0.75
     im
    -0.73
     non
    -0.71
    Ab
    -0.71
    ḗ
    -0.70
     bort
    -0.70
     oh
    -0.70
    POSITIVE LOGITS
     Wuhan
    1.64
     Pandemic
    1.30
     zoon
    1.24
     virus
    1.13
     Huan
    1.07
     bat
    1.04
     Virology
    1.03
     bats
    1.02
     China
    1.02
     viro
    1.01
    Activations Density 0.008%

    No Known Activations