© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120064
    Prev
    Next
    INDEX
    Explanations

    countries and the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     questions
    -0.06
     оба
    -0.06
     précieux
    -0.06
    questions
    -0.06
    ทั้ง
    -0.06
    行業
    -0.05
     indispensable
    -0.05
     new
    -0.05
    岌
    -0.05
    /%
    -0.05
    POSITIVE LOGITS
     ограничи
    0.06
     অনেকটা
    0.06
     ogran
    0.06
    imizi
    0.06
     modestly
    0.06
     допъл
    0.06
    数百
    0.06
    あまり
    0.06
     ở
    0.05
     manchmal
    0.05
    Activations Density 0.023%

    No Known Activations