© 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. 117068
    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
     وم
    -0.07
     клини
    -0.06
    draft
    -0.06
     nuestras
    -0.06
     ६
    -0.06
     documentaire
    -0.06
    日本語
    -0.05
     всички
    -0.05
    んに
    -0.05
     clinical
    -0.05
    POSITIVE LOGITS
    consider
    0.07
     గొప్ప
    0.07
     GUS
    0.07
     ancak
    0.07
     dů
    0.06
     gradually
    0.06
    presumably
    0.06
     GPs
    0.06
     consider
    0.06
    וּ
    0.06
    Activations Density 0.000%

    No Known Activations