© 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. 63645
    Prev
    Next
    INDEX
    Explanations

    Germany, Russia, Britain, Italy, China, France

    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
    多次
    -1.05
     idee
    -1.02
     великолеп
    -0.98
     cilindros
    -0.98
    皆さん
    -0.96
     її
    -0.95
    #%%
    -0.95
    %[
    -0.93
     Transfermarkt
    -0.93
     دهید
    -0.93
    POSITIVE LOGITS
     Germany
    1.88
     Russia
    1.75
     British
    1.75
     Britain
    1.75
     Italy
    1.59
     Brazil
    1.59
     China
    1.59
     California
    1.57
     Japan
    1.56
     France
    1.55
    Activations Density 0.140%

    No Known Activations