© 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. 128461
    Prev
    Next
    INDEX
    Explanations

    international appearances

    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
     다음
    -0.06
    containers
    -0.06
     然后
    -0.06
     pungent
    -0.06
    他在
    -0.06
     그는
    -0.06
    个人的
    -0.06
    奪
    -0.05
    Цена
    -0.05
     البشر
    -0.05
    POSITIVE LOGITS
     becoming
    0.07
     divent
    0.07
     ተጨማሪ
    0.07
     joining
    0.07
     Become
    0.06
     devenir
    0.06
    Ợ
    0.06
     linking
    0.06
     எங்கள்
    0.06
     கூடுதல்
    0.06
    Activations Density 0.010%

    No Known Activations