© 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. 96430
    Prev
    Next
    INDEX
    Explanations

    foreign countries and geography

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

    map versus territory

    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
     бухгал
    0.52
    抢
    0.50
     балан
    0.49
    
    0.48
     кожного
    0.48
    總
    0.48
     машины
    0.47
    кового
    0.47
    ✼
    0.47
    𝗗
    0.47
    POSITIVE LOGITS
    turkish
    0.50
    iterranean
    0.44
     Europeans
    0.44
     Palestinian
    0.44
    ksa
    0.43
    ındaki
    0.43
    docker
    0.42
    alkan
    0.42
     kios
    0.42
     stöd
    0.42
    Activations Density 0.001%

    No Known Activations