© 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. 116419
    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
     aspect
    -0.07
    aspect
    -0.07
    %">
    -0.06
    甚至是
    -0.06
    Tovar
    -0.06
     даних
    -0.06
     duż
    -0.06
     embarked
    -0.06
     Aspects
    -0.06
     возможных
    -0.06
    POSITIVE LOGITS
     هنوز
    0.06
     Acupuncture
    0.06
    Still
    0.06
     ainda
    0.06
     still
    0.06
     ionized
    0.06
     injections
    0.06
     SEX
    0.06
     satu
    0.06
     আর্জেন্টিনা
    0.06
    Activations Density 0.000%

    No Known Activations