© 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. 117110
    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
    敌
    -0.07
    Этот
    -0.06
     этот
    -0.06
     కొత్త
    -0.06
    发放
    -0.06
    每個
    -0.06
    мона
    -0.06
    ൌ
    -0.06
    elves
    -0.06
    vió
    -0.06
    POSITIVE LOGITS
     शिव
    0.06
     BL
    0.05
     finalmente
    0.05
     Gar
    0.05
    ANDO
    0.05
     উচ্চারণ
    0.05
     PL
    0.05
     finally
    0.05
     áll
    0.05
     magari
    0.05
    Activations Density 0.000%

    No Known Activations