© 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. 65984
    Prev
    Next
    INDEX
    Explanations

    former soviet bloc countries

    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
    achev
    -0.98
     ২০১
    -0.95
    VideoView
    -0.90
     software
    -0.82
    ethanol
    -0.81
    左手
    -0.79
    logeny
    -0.79
    purple
    -0.79
     online
    -0.79
     divertida
    -0.78
    POSITIVE LOGITS
     Yugoslav
    1.10
     Yugoslavia
    1.01
     Yugos
    0.94
     Czechoslovakia
    0.93
     Czechos
    0.92
     USSR
    0.88
     jugos
    0.87
     Jugos
    0.84
    Soviet
    0.82
     Uran
    0.82
    Activations Density 0.060%

    No Known Activations