© 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. 117715
    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
     intención
    -0.07
    设计的
    -0.06
     শীঘ্রই
    -0.06
    従来の
    -0.06
    ):=\
    -0.06
    /
    -0.06
     ursprüng
    -0.06
    最优
    -0.06
     مذکور
    -0.06
    но
    -0.06
    POSITIVE LOGITS
     questa
    0.07
    utt
    0.07
     which
    0.06
     byen
    0.06
     दुख
    0.06
    [{{
    0.06
     لاعب
    0.06
     HMS
    0.06
     філь
    0.06
     varje
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.