© 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. 117594
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
     incoming
    -0.06
     дета
    -0.06
     initiating
    -0.06
    Incoming
    -0.06
     Incoming
    -0.06
    \}_{
    -0.06
    Ward
    -0.06
    Whatever
    -0.06
    wych
    -0.05
     whatever
    -0.05
    POSITIVE LOGITS
     recommandé
    0.06
     combine
    0.06
    विद्यालय
    0.06
     multiple
    0.06
     recommandée
    0.06
     প্রধানমন্ত্রীর
    0.06
     recommended
    0.06
    multiple
    0.06
     comand
    0.06
     paintbrush
    0.06
    Activations Density 0.029%

    No Known Activations