© 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. 128557
    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
     ở
    -0.06
     skrev
    -0.06
    ্লিষ্ট
    -0.06
     எழுதி
    -0.06
     vậy
    -0.06
     दूसरी
    -0.06
    但
    -0.06
    આ
    -0.06
    Não
    -0.06
     добавить
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.07
    finding
    0.06
     finding
    0.06
     phosphatase
    0.06
     paramilitary
    0.06
    getParameter
    0.06
    existsSync
    0.05
     firsthand
    0.05
     Prime
    0.05
     va
    0.05
    Activations Density 0.000%

    No Known Activations