© 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. 128430
    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
    thousands
    -0.06
     hundreds
    -0.06
    medical
    -0.06
     millions
    -0.06
     shutterstock
    -0.06
     расходы
    -0.06
     other
    -0.06
     costing
    -0.06
     Other
    -0.06
    राल
    -0.06
    POSITIVE LOGITS
     †
    0.07
     pertinent
    0.06
     hacia
    0.06
    Mexican
    0.06
     लाइन
    0.06
     variational
    0.06
     leisurely
    0.06
     congrat
    0.06
     ascertaining
    0.06
     **,
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.