© 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. 119488
    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
     When
    -0.06
    Jh
    -0.06
     മല
    -0.06
    episode
    -0.06
    每一个
    -0.06
     conocidos
    -0.06
     pyt
    -0.06
    Maar
    -0.06
     mares
    -0.06
     incluyendo
    -0.06
    POSITIVE LOGITS
     neue
    0.07
     neuen
    0.06
     difficulties
    0.06
     новые
    0.06
    صدر
    0.06
    他又
    0.06
    ability
    0.06
     yeni
    0.06
     nieuwe
    0.06
     ആള
    0.06
    Activations Density 0.000%

    No Known Activations