© 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. 119949
    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
     differentially
    -0.06
    жела
    -0.06
     приват
    -0.06
     விழுப்பு
    -0.06
     상세
    -0.06
     Flanders
    -0.06
     afbeelding
    -0.06
     자세
    -0.06
     Naga
    -0.05
    ENCIA
    -0.05
    POSITIVE LOGITS
    ښت
    0.06
     Nhưng
    0.06
    ෙන්ම
    0.06
    可惜
    0.06
     কোনটি
    0.06
     teatro
    0.06
    㕕
    0.06
     সবই
    0.06
     ಸರ್ಕಾರದ
    0.06
     অর্থনৈতিক
    0.06
    Activations Density 0.000%

    No Known Activations