© 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. 130662
    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
     majest
    -0.06
     włas
    -0.06
     histories
    -0.06
    endereco
    -0.06
     ಅಧಿಕ
    -0.06
     दोन
    -0.06
    épaisseur
    -0.06
    hasil
    -0.06
     Ис
    -0.06
    瑁
    -0.06
    POSITIVE LOGITS
    ough
    0.06
     periodic
    0.06
     अनुया
    0.06
    Usually
    0.06
     সাধারণত
    0.06
     новой
    0.06
     kawaida
    0.06
     Submit
    0.06
    achte
    0.06
     newsletters
    0.06
    Activations Density 0.000%

    No Known Activations