© 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. 120339
    Prev
    Next
    INDEX
    Explanations

    xoreos

    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
    提高了
    -0.07
     puissant
    -0.07
     শক্তিশালী
    -0.07
    贡献
    -0.07
     चैंपियनशिप
    -0.07
     설치
    -0.06
     upgraded
    -0.06
    安装
    -0.06
    Usually
    -0.06
     केलेल्या
    -0.06
    POSITIVE LOGITS
     data
    0.06
    ↵
    0.06
     communications
    0.06
     spies
    0.05
     ক্রিয়া
    0.05
     Data
    0.05
     hectic
    0.05
     Io
    0.05
     начать
    0.05
    data
    0.05
    Activations Density 0.003%

    No Known Activations