© 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. 116277
    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
    一些
    -0.08
    Some
    -0.07
     some
    -0.07
    那些
    -0.07
     어떤
    -0.07
    if
    -0.07
     since
    -0.07
    since
    -0.07
    not
    -0.06
    routes
    -0.06
    POSITIVE LOGITS
     économ
    0.07
    甥
    0.06
     leur
    0.06
     consulté
    0.06
     прошу
    0.06
     celý
    0.06
     Constructed
    0.06
     oğlu
    0.06
     несмотря
    0.06
     amput
    0.06
    Activations Density 0.000%

    No Known Activations