© 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. 128704
    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
     ANYTHING
    -0.07
    一组
    -0.06
     രാ
    -0.06
    querda
    -0.06
    стары
    -0.06
    anything
    -0.06
    するのは
    -0.06
    ειας
    -0.06
     anything
    -0.06
     الخاصة
    -0.06
    POSITIVE LOGITS
    罪
    0.06
     prior
    0.06
     सुकून
    0.06
     такую
    0.06
     fundamentally
    0.06
     such
    0.06
     неболь
    0.06
     زيد
    0.06
     improve
    0.06
    football
    0.06
    Activations Density 0.000%

    No Known Activations