© 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. 128764
    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
     for
    -0.07
     in
    -0.07
     sklearn
    -0.06
     battles
    -0.06
     Battles
    -0.06
    ப்பட்டுள்ள
    -0.06
     atrap
    -0.06
     Rech
    -0.05
     चंद्र
    -0.05
     moh
    -0.05
    POSITIVE LOGITS
     devrait
    0.06
     چنین
    0.06
    WithSize
    0.06
     certainly
    0.06
     debería
    0.06
     таке
    0.06
    মন্দ
    0.06
     með
    0.06
    라고
    0.06
     exteriores
    0.06
    Activations Density 0.000%

    No Known Activations