© 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. 116686
    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
     Giants
    -0.07
     DRIVE
    -0.06
     प्रैक्टिस
    -0.06
     thirty
    -0.06
     intestine
    -0.06
    🌧
    -0.06
    giants
    -0.06
    すぐに
    -0.06
    数は
    -0.06
    馬上
    -0.06
    POSITIVE LOGITS
     シンプル
    0.07
     सफलतापूर्वक
    0.06
     сана
    0.06
     enfl
    0.06
     ensured
    0.06
     unle
    0.06
     ensuring
    0.06
     ensures
    0.06
     sati
    0.06
     使用
    0.06
    Activations Density 0.000%

    No Known Activations