© 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. 128658
    Prev
    Next
    INDEX
    Explanations

    app developer

    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
     включают
    -0.06
    允許
    -0.06
     fő
    -0.06
     çerçe
    -0.06
     groundwork
    -0.06
    ための
    -0.06
     incluyen
    -0.06
     allows
    -0.06
     speeds
    -0.06
     formData
    -0.06
    POSITIVE LOGITS
     most
    0.07
     usability
    0.06
    ruar
    0.06
     critically
    0.06
    iOS
    0.06
    vius
    0.06
     published
    0.06
     গুন
    0.06
     ناقابل
    0.06
    plist
    0.06
    Activations Density 0.013%

    No Known Activations