© 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. 119472
    Prev
    Next
    INDEX
    Explanations

    url paths (.com, .org, .net)

    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
     постоянно
    -0.06
     पांच
    -0.06
     చాలా
    -0.06
     регулярно
    -0.06
    ínu
    -0.06
     permanently
    -0.06
    5
    -0.06
     समय
    -0.06
     પોતાના
    -0.06
     सीधे
    -0.06
    POSITIVE LOGITS
    slides
    0.06
     allure
    0.06
    ORIG
    0.06
    ◦
    0.06
     words
    0.06
     HAVE
    0.06
    newLine
    0.06
     ditulis
    0.06
     সৃষ্টির
    0.06
     jusqu
    0.06
    Activations Density 0.001%

    No Known Activations