© 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. 129554
    Prev
    Next
    INDEX
    Explanations

    epigenetic changes and regulation

    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
     좋은
    -0.07
    탰
    -0.07
     áreas
    -0.07
     부동산
    -0.07
    小さな
    -0.07
    ब्रा
    -0.07
    爱好者
    -0.07
    浏览器
    -0.06
    investissement
    -0.06
     vært
    -0.06
    POSITIVE LOGITS
     இப்பட
    0.06
     Independ
    0.06
     
    0.05
    ”
    0.05
    refer
    0.05
    மின்றி
    0.05
     случа
    0.05
    slide
    0.05
     additional
    0.05
     تحصل
    0.05
    Activations Density 0.004%

    No Known Activations