© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118641
    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
    Während
    -0.07
     coloque
    -0.07
     polinom
    -0.06
     mezcl
    -0.06
    Vý
    -0.06
     discours
    -0.06
     nějak
    -0.06
    マル
    -0.06
    ではなく
    -0.06
     Vý
    -0.06
    POSITIVE LOGITS
     これ
    0.07
     nailed
    0.06
    すべて
    0.06
     Mohammed
    0.05
    于
    0.05
    すぐ
    0.05
     오는
    0.05
     even
    0.05
     অর্জন
    0.05
     mostly
    0.05
    Activations Density 0.000%

    No Known Activations