© 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. 129403
    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
     również
    -0.07
     גם
    -0.07
     arī
    -0.07
     that
    -0.06
     যে
    -0.06
     që
    -0.06
     also
    -0.06
    enberg
    -0.06
     cũng
    -0.06
     też
    -0.06
    POSITIVE LOGITS
     at
    0.06
     musste
    0.06
    Closed
    0.06
    வசம்
    0.05
     between
    0.05
     DIY
    0.05
    vous
    0.05
    Username
    0.05
    Aim
    0.05
     ताल
    0.05
    Activations Density 0.000%

    No Known Activations