© 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. 84317
    Prev
    Next
    INDEX
    Explanations

    countries after and

    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
     США
    -2.08
    アメリカ
    -1.98
    美國
    -1.83
     USA
    -1.80
    美国
    -1.70
    USA
    -1.70
     американ
    -1.66
     america
    -1.58
    США
    -1.57
     usa
    -1.55
    POSITIVE LOGITS
     Europe
    2.17
     Canada
    2.14
     European
    1.93
     Canadian
    1.72
     Britain
    1.69
     Australia
    1.53
    Europe
    1.53
     UK
    1.49
     British
    1.48
    Canada
    1.48
    Activations Density 0.071%

    No Known Activations