© 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. 119099
    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
     so
    -0.06
     career
    -0.06
     last
    -0.06
     여성
    -0.06
     রেকর্ড
    -0.06
     ending
    -0.06
     마지막
    -0.06
     filming
    -0.06
     самый
    -0.06
     greatest
    -0.06
    POSITIVE LOGITS
     viac
    0.06
     simple
    0.06
     yourselves
    0.06
    を用いて
    0.06
     baits
    0.06
     sufficiently
    0.06
    增加了
    0.06
     consented
    0.06
     plain
    0.06
     peeps
    0.06
    Activations Density 0.000%

    No Known Activations