© 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. 117311
    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
     შეიძლება
    -0.07
     može
    -0.06
     يمكن
    -0.06
     может
    -0.06
     maaaring
    -0.06
    に
    -0.06
    可以
    -0.05
    によって
    -0.05
    อาจ
    -0.05
    Lib
    -0.05
    POSITIVE LOGITS
     такие
    0.06
     However
    0.06
     verify
    0.06
     multiple
    0.06
     Это
    0.06
     স্বেচ্ছ
    0.06
     permiten
    0.06
    ffineTransform
    0.06
     そんな
    0.06
     Programa
    0.06
    Activations Density 0.000%

    No Known Activations