© 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. 119409
    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
    !\
    -0.07
     sterk
    -0.07
     encourage
    -0.07
     enthusiastic
    -0.06
     underwent
    -0.06
     khó
    -0.06
     برای
    -0.06
    
    -0.06
     invigor
    -0.06
    !;
    -0.06
    POSITIVE LOGITS
    忠
    0.06
     중간
    0.06
    தின
    0.06
     integration
    0.05
    ทุก
    0.05
     setiap
    0.05
     আজকে
    0.05
    hidden
    0.05
     duration
    0.05
     disappeared
    0.05
    Activations Density 0.000%

    No Known Activations