© 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. 119918
    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
    appreciated
    -0.06
     již
    -0.06
    讚
    -0.06
    acquisition
    -0.06
     Never
    -0.06
     தாய்
    -0.06
     White
    -0.06
     appreciate
    -0.06
     amassed
    -0.05
     appreciating
    -0.05
    POSITIVE LOGITS
     it
    0.07
     hampir
    0.06
    ☀️
    0.06
     è
    0.06
     accordingly
    0.06
     constitucional
    0.06
     เช่น
    0.06
    👶
    0.06
     يبقى
    0.06
     hvor
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.