© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130572
    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
     مؤثر
    -0.06
     Guinness
    -0.06
     surprising
    -0.06
    佢
    -0.06
     بينما
    -0.06
    竟然
    -0.06
     unanimous
    -0.06
     Revealed
    -0.05
    感慨
    -0.05
     überras
    -0.05
    POSITIVE LOGITS
     villes
    0.08
    ⚊
    0.06
     venerable
    0.06
     স্কুল
    0.06
     would
    0.06
     strife
    0.06
     Warnings
    0.06
     berbagai
    0.06
     repository
    0.06
     généraux
    0.06
    Activations Density 0.000%

    No Known Activations