© 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. 7113
    Prev
    Next
    INDEX
    Explanations

    nationalities and their origins

    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
     rano
    -0.93
     Explains
    -0.93
    retched
    -0.82
     approximate
    -0.82
     barons
    -0.82
     électron
    -0.81
    Вопросы
    -0.80
     discerned
    -0.80
     ravens
    -0.79
     alpes
    -0.79
    POSITIVE LOGITS
     immigrant
    1.23
     immigrants
    1.00
    American
    0.93
     prince
    0.93
     их
    0.93
     their
    0.92
    Americans
    0.91
     memakai
    0.90
    裔
    0.88
     American
    0.84
    Activations Density 0.076%

    No Known Activations