© 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. 116854
    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
     Flowering
    -0.06
    piry
    -0.06
    ETHER
    -0.06
    ībā
    -0.06
     tuvo
    -0.06
     JAPAN
    -0.06
    ಾರದ
    -0.06
    šina
    -0.06
     कागज
    -0.06
    শ্ত
    -0.06
    POSITIVE LOGITS
     so
    0.06
    around
    0.06
     নির্যাতন
    0.06
     Improvements
    0.06
    More
    0.06
    สอน
    0.06
     improvements
    0.06
     (
    0.05
     placing
    0.05
    اس
    0.05
    Activations Density 0.000%

    No Known Activations