© 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. 117233
    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
    ().
    -0.06
     وهو
    -0.06
     материал
    -0.06
     "").
    -0.06
    ůj
    -0.06
    𝚐
    -0.06
     защото
    -0.06
     इसको
    -0.06
     العناصر
    -0.06
    还要
    -0.06
    POSITIVE LOGITS
    äten
    0.06
    meer
    0.06
    文字
    0.06
     আশেপাশে
    0.06
     damal
    0.06
     enca
    0.06
    acknowledge
    0.06
    当时的
    0.06
     चुका
    0.06
     nagu
    0.06
    Activations Density 0.000%

    No Known Activations