© 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. 128355
    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
     Leute
    -0.06
     방법을
    -0.06
    这些
    -0.06
    要是
    -0.06
     metodo
    -0.06
     puno
    -0.06
    ೪
    -0.06
    假如
    -0.06
    словно
    -0.06
    这种
    -0.06
    POSITIVE LOGITS
     have
    0.06
     ব্যপারে
    0.06
     περισσότε
    0.06
     most
    0.06
     argument
    0.06
     more
    0.05
     has
    0.05
     Karate
    0.05
    hooting
    0.05
     scipy
    0.05
    Activations Density 0.000%

    No Known Activations