© 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. 129132
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    สาม
    -0.07
     Allows
    -0.07
     аутох
    -0.06
     nghe
    -0.06
     permite
    -0.06
     allows
    -0.06
     вход
    -0.06
     General
    -0.06
     elucidate
    -0.06
     chevron
    -0.06
    POSITIVE LOGITS
    趔
    0.06
     जितना
    0.06
     hareket
    0.05
     છીએ
    0.05
     precautions
    0.05
     పోలీ
    0.05
     जितनी
    0.05
    የር
    0.05
    ㅠㅠ
    0.05
    YU
    0.05
    Activations Density 0.000%

    No Known Activations