© 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. 128927
    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
     your
    -0.07
     swoich
    -0.07
     swoje
    -0.07
    等等
    -0.06
    தெ
    -0.06
     être
    -0.06
    自分の
    -0.06
    自己的
    -0.06
     για
    -0.06
    还要
    -0.06
    POSITIVE LOGITS
     மக்கள்
    0.06
     only
    0.06
    予算
    0.05
     produkty
    0.05
    ̖
    0.05
     (
    0.05
    ioides
    0.05
    ٘
    0.05
    RODUCTION
    0.05
     তরুণ
    0.05
    Activations Density 0.000%

    No Known Activations