© 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. 117502
    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
     الحكوم
    -0.06
     কেবল
    -0.06
     delegates
    -0.06
    에서도
    -0.06
               
    -0.06
     niệm
    -0.06
     кроме
    -0.06
    atorship
    -0.06
     abajo
    -0.05
     sail
    -0.05
    POSITIVE LOGITS
     incidentally
    0.07
     inadvertently
    0.06
     Puede
    0.06
     bioc
    0.06
     bzw
    0.05
     effective
    0.05
    رک
    0.05
    υχ
    0.05
     পাকিস্তানী
    0.05
     it
    0.05
    Activations Density 0.000%

    No Known Activations