© 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. 117358
    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
     ಇತರ
    -0.08
     ሌሎች
    -0.07
    شان
    -0.07
    within
    -0.07
    includes
    -0.07
    always
    -0.07
     להיות
    -0.07
     alltid
    -0.07
    ภายใน
    -0.07
     από
    -0.06
    POSITIVE LOGITS
     stomp
    0.06
     greenish
    0.06
     who
    0.06
     conhecimentos
    0.06
     #[
    0.06
     नॉलेज
    0.05
     हाम
    0.05
     whose
    0.05
     horsepower
    0.05
    呱
    0.05
    Activations Density 0.000%

    No Known Activations