© 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. 117659
    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
    完整
    -0.06
    ,
    -0.06
    แต่
    -0.05
     lahat
    -0.05
     प्रवेश
    -0.05
     apesar
    -0.05
     প্রাকৃতিক
    -0.05
    oyer
    -0.05
     Been
    -0.05
    pesar
    -0.05
    POSITIVE LOGITS
    是非常
    0.07
     tumor
    0.07
    उनकी
    0.07
     skit
    0.06
     নেওয়া
    0.06
     appena
    0.06
     дуже
    0.06
     ಸರ್ಕಾರದ
    0.06
     just
    0.06
     ভিতরে
    0.06
    Activations Density 0.000%

    No Known Activations