© 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. 116836
    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
     сочета
    -0.06
     লৌ
    -0.06
     hemod
    -0.06
     வெவ்வேறு
    -0.06
    As
    -0.06
     roaming
    -0.06
     depictions
    -0.05
     handicapped
    -0.05
     named
    -0.05
     எவ்வாறு
    -0.05
    POSITIVE LOGITS
    ↵
    0.13
    .
    0.06
    噤
    0.06
     امریک
    0.06
     امریکی
    0.06
    ının
    0.06
     not
    0.06
    ↵↵↵
    0.06
     undeniable
    0.06
    ។
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.