© 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. 128565
    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
     말고
    -0.06
     explaining
    -0.06
    guard
    -0.06
    num
    -0.06
     রক্ত
    -0.06
     요구
    -0.06
     proportion
    -0.06
     uttering
    -0.06
     zid
    -0.06
     investigations
    -0.06
    POSITIVE LOGITS
     Run
    0.06
    resonant
    0.06
     fragile
    0.06
    啥
    0.06
    beige
    0.06
     fluffy
    0.06
    อิน
    0.06
     CONSTRAINT
    0.06
    家居
    0.06
    chell
    0.06
    Activations Density 0.000%

    No Known Activations