© 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. 117718
    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
    ではなく
    -0.06
    有过
    -0.06
     مكتب
    -0.06
     kemungkinan
    -0.06
     distanza
    -0.06
    ),
    -0.06
     opção
    -0.06
     non
    -0.06
    ःख
    -0.06
     stepped
    -0.06
    POSITIVE LOGITS
     information
    0.05
     அவை
    0.05
    Welcome
    0.05
     இரண்டு
    0.05
    Could
    0.05
    ֥
    0.05
     Hayashi
    0.05
    ص
    0.05
     informa
    0.05
     रूपये
    0.05
    Activations Density 0.000%

    No Known Activations