© 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. 119970
    Prev
    Next
    INDEX
    Explanations

    legal citations and court documents

    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
    利用
    -0.06
     claim
    -0.06
     استخدم
    -0.06
     uporab
    -0.06
    人之
    -0.06
    ব্যবহার
    -0.06
     wykorzyst
    -0.06
    ابط
    -0.06
    [
    -0.05
     первых
    -0.05
    POSITIVE LOGITS
     increasing
    0.06
     chúng
    0.06
    WITH
    0.06
    ürzt
    0.06
     மீண்டும்
    0.06
     możemy
    0.06
     разработан
    0.06
     आवश्यकता
    0.06
     phasing
    0.06
    जिसे
    0.06
    Activations Density 0.001%

    No Known Activations