© 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. 129349
    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
     under
    -0.08
     high
    -0.06
     low
    -0.06
     High
    -0.06
     snel
    -0.06
    高
    -0.06
    under
    -0.05
     ऊंचा
    -0.05
     tijd
    -0.05
    High
    -0.05
    POSITIVE LOGITS
     også
    0.07
     например
    0.07
     aritmética
    0.07
     isinstance
    0.07
     също
    0.06
     explorers
    0.06
     Fukuoka
    0.06
     également
    0.06
    IZATION
    0.06
     tambien
    0.06
    Activations Density 0.000%

    No Known Activations