© 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. 119427
    Prev
    Next
    INDEX
    Explanations

    technical/instructional document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     известные
    -0.06
     முற
    -0.06
     посредством
    -0.06
     Championships
    -0.06
     membres
    -0.06
     using
    -0.06
    application
    -0.05
    ieres
    -0.05
     Anthony
    -0.05
     championships
    -0.05
    POSITIVE LOGITS
     decommissioning
    0.06
     gleichzeitig
    0.06
    dwm
    0.06
     الخدمات
    0.06
     Protect
    0.06
    щину
    0.06
     Länge
    0.06
     disordered
    0.06
    車の
    0.06
     protect
    0.06
    Activations Density 0.005%

    No Known Activations