© 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. 129293
    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
    亚博
    -0.06
     최고의
    -0.06
     as
    -0.06
     nabí
    -0.06
    পিং
    -0.05
     with
    -0.05
     magní
    -0.05
     ক্ষুধার
    -0.05
    ங்களாக
    -0.05
     উৎক
    -0.05
    POSITIVE LOGITS
     new
    0.08
     nötig
    0.07
     ощущения
    0.06
     ナチュラル
    0.06
     necessary
    0.06
     small
    0.06
     žene
    0.06
    少
    0.06
     gesamte
    0.06
     women
    0.06
    Activations Density 0.000%

    No Known Activations