© 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. 120203
    Prev
    Next
    INDEX
    Explanations

    configuration file and property settings

    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
     প্রথমবারের
    -0.06
    となった
    -0.06
     möglichst
    -0.06
     atraves
    -0.06
     qualifier
    -0.06
     queim
    -0.06
     मुफ्त
    -0.06
    చిత
    -0.06
    webElementGuid
    -0.06
     type
    -0.06
    POSITIVE LOGITS
    🐳
    0.07
     answers
    0.06
     ellos
    0.06
     ديسمبر
    0.06
     ત્રણ
    0.06
    🐋
    0.06
    arked
    0.06
    descriptions
    0.06
     какие
    0.06
    setDescription
    0.06
    Activations Density 0.009%

    No Known Activations