© 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. 119457
    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
     داریم
    -0.07
    很多
    -0.06
     있는데
    -0.06
     frei
    -0.06
    ফাজ
    -0.06
    ⋄
    -0.06
     Diaspora
    -0.06
     unve
    -0.06
    glio
    -0.06
     Dorian
    -0.06
    POSITIVE LOGITS
     ಮಕ್ಕಳ
    0.06
     womens
    0.06
    family
    0.06
    增强
    0.06
    辱
    0.06
     perímetro
    0.06
     csal
    0.06
    multi
    0.06
     altogether
    0.06
     kvinn
    0.06
    Activations Density 0.000%

    No Known Activations