© 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. 119957
    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
    嚐
    -0.06
     could
    -0.06
     trader
    -0.06
     Thing
    -0.06
     multinational
    -0.06
     marques
    -0.06
    Capable
    -0.06
     honom
    -0.06
     বিয়ে
    -0.05
    mason
    -0.05
    POSITIVE LOGITS
    虽然
    0.07
    although
    0.07
    бро
    0.06
     لإ
    0.06
    一直
    0.06
     iako
    0.06
     fullness
    0.06
     although
    0.06
    一定要
    0.06
    How
    0.06
    Activations Density 0.000%

    No Known Activations