© 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. 130637
    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
     সাফল্যের
    -0.07
     Harsh
    -0.06
    但是我
    -0.06
     असता
    -0.06
     already
    -0.06
     unwarrant
    -0.06
     contenuto
    -0.06
     MEDIA
    -0.06
     photoshop
    -0.06
    🩸
    -0.06
    POSITIVE LOGITS
     навыки
    0.06
     etc
    0.06
     ◇
    0.06
     vše
    0.06
     revanche
    0.06
    ◇
    0.06
     responds
    0.06
     all
    0.06
    など
    0.05
     निकट
    0.05
    Activations Density 0.000%

    No Known Activations