© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73690
    Prev
    Next
    INDEX
    Explanations

    Czech Republic and related geography

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

    Czech and related places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mesopot
    0.50
     Афри
    0.47
    ビーチ
    0.47
    綢
    0.45
    起点
    0.44
    Imagem
    0.44
     Pantai
    0.44
     Pensacola
    0.44
     উপকূল
    0.43
    锵
    0.43
    POSITIVE LOGITS
     Czech
    1.77
    Czech
    1.53
     Czechoslovak
    1.49
     Brno
    1.48
     Prague
    1.45
     Czechoslovakia
    1.44
     česk
    1.34
    Czechoslovakia
    1.27
     České
    1.27
     Česk
    1.27
    Activations Density 0.054%

    No Known Activations