© 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. 118346
    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
    ВО
    -0.06
     особли
    -0.06
     obser
    -0.06
     nuestro
    -0.06
     наш
    -0.06
     особы
    -0.06
     générations
    -0.05
    実際の
    -0.05
     ವರ್ಗ
    -0.05
     हमारी
    -0.05
    POSITIVE LOGITS
     medios
    0.06
     zoo
    0.06
     Zoo
    0.06
     hostel
    0.06
    matmul
    0.06
    iguo
    0.06
     embarrass
    0.06
     if
    0.06
     Haynes
    0.06
     اگر
    0.06
    Activations Density 0.000%

    No Known Activations