© 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. 128535
    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
    There
    -0.06
     main
    -0.06
    大部分
    -0.06
    也有
    -0.06
    几乎
    -0.06
     spä
    -0.06
     également
    -0.06
     ruins
    -0.06
    メイン
    -0.06
     there
    -0.05
    POSITIVE LOGITS
     uncompromising
    0.07
     multilingual
    0.07
     تحقق
    0.06
    VES
    0.06
     VMs
    0.06
     projector
    0.05
     contender
    0.05
     feasibility
    0.05
    '<
    0.05
    вих
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.