© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120723
    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
     using
    -0.07
     із
    -0.07
     auch
    -0.07
    兩
    -0.07
    ต่าง
    -0.06
     باستخدام
    -0.06
     생각
    -0.06
     egy
    -0.06
     OS
    -0.06
     ৬
    -0.06
    POSITIVE LOGITS
    same
    0.05
    pho
    0.05
    決して
    0.05
     or
    0.05
    市政
    0.05
     často
    0.05
     যেগুলো
    0.05
     அவள்
    0.05
    much
    0.05
     hjæl
    0.05
    Activations Density 0.000%

    No Known Activations