© 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. 119601
    Prev
    Next
    INDEX
    Explanations

    months

    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
    重大
    -0.07
     Prints
    -0.06
     مشتر
    -0.06
     major
    -0.06
    Prints
    -0.06
     ông
    -0.06
    orthogonal
    -0.06
     سواء
    -0.06
    较大
    -0.06
     خودرو
    -0.06
    POSITIVE LOGITS
     first
    0.07
     eventually
    0.07
     eerste
    0.06
    -]+
    0.06
    সরকারী
    0.06
    最初に
    0.06
     abiding
    0.06
     первое
    0.06
    🇨
    0.06
     thriving
    0.06
    Activations Density 0.005%

    No Known Activations