© 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. 119267
    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
    ydent
    -0.06
    ڨ
    -0.06
    四个
    -0.06
    ちゃう
    -0.06
     ಇದನ್ನು
    -0.06
    Banner
    -0.06
     tempted
    -0.06
     Therefore
    -0.05
     banget
    -0.05
     sails
    -0.05
    POSITIVE LOGITS
     눈
    0.07
    なぜ
    0.06
     업체
    0.06
     feline
    0.06
     what
    0.06
     حدود
    0.06
     konus
    0.06
     이유는
    0.06
     an
    0.06
     ప్రక
    0.06
    Activations Density 0.000%

    No Known Activations