© 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. 128382
    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
     tìm
    -0.06
    被
    -0.06
     deine
    -0.06
     Jó
    -0.06
     paradig
    -0.06
     regrett
    -0.06
    许多
    -0.06
    说道
    -0.06
     új
    -0.06
    之前
    -0.06
    POSITIVE LOGITS
    টাও
    0.07
     managable
    0.06
    icone
    0.06
     Finish
    0.06
    iomanip
    0.06
    fut
    0.06
    5
    0.06
    !?
    0.06
     wholesome
    0.06
     चिंतित
    0.06
    Activations Density 0.000%

    No Known Activations