© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130850
    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
     ранее
    -0.07
     anteriores
    -0.07
     শরত
    -0.07
    覬
    -0.07
     ständig
    -0.07
     மற்றொரு
    -0.06
     riun
    -0.06
     riego
    -0.06
    previously
    -0.06
     этими
    -0.06
    POSITIVE LOGITS
     includes
    0.06
     type
    0.06
     località
    0.06
     wasn
    0.05
     What
    0.05
     what
    0.05
    を目指
    0.05
     aims
    0.05
     Includes
    0.05
     dolore
    0.05
    Activations Density 0.000%

    No Known Activations