© 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. 128392
    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
     просто
    -0.06
     karena
    -0.06
     certified
    -0.06
     kerana
    -0.06
     장애
    -0.06
     вас
    -0.06
     nowych
    -0.06
    şağı
    -0.06
     новым
    -0.05
     zase
    -0.05
    POSITIVE LOGITS
     while
    0.07
     when
    0.06
     continually
    0.06
     Tüm
    0.06
     underlying
    0.06
    िलास
    0.06
    sourceforge
    0.06
     tainted
    0.06
    frmt
    0.06
     beim
    0.05
    Activations Density 0.000%

    No Known Activations