© 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. 120475
    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
     a
    -0.08
     an
    -0.07
     başka
    -0.06
     another
    -0.06
     associé
    -0.06
     pertinent
    -0.06
     später
    -0.06
     вмеша
    -0.06
     wspom
    -0.06
    মেয়ে
    -0.06
    POSITIVE LOGITS
    只
    0.07
     only
    0.07
     tikai
    0.07
     chỉ
    0.07
    Only
    0.07
     फक्त
    0.07
    only
    0.06
    只有
    0.06
    只能
    0.06
     فقط
    0.06
    Activations Density 0.000%

    No Known Activations