© 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. 117267
    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
     excitement
    -0.08
     Interesse
    -0.06
     intent
    -0.06
     inicialmente
    -0.06
    culture
    -0.06
     возбу
    -0.06
     института
    -0.06
     originated
    -0.06
     before
    -0.06
     vandalism
    -0.06
    POSITIVE LOGITS
    限制
    0.08
     restricting
    0.07
     restrict
    0.07
     शिकायतों
    0.07
     제한
    0.06
    restrictions
    0.06
     disables
    0.06
    缺点
    0.06
     hindering
    0.06
     restricts
    0.06
    Activations Density 0.000%

    No Known Activations