© 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. 117674
    Prev
    Next
    INDEX
    Explanations

    debris falling

    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
     purposely
    -0.06
     वायु
    -0.06
     deliberately
    -0.06
     israel
    -0.06
     आपण
    -0.06
     by
    -0.06
     seventies
    -0.06
    ണ്ണം
    -0.06
     сайта
    -0.06
    留下
    -0.06
    POSITIVE LOGITS
     minori
    0.06
    》《
    0.06
     Morocco
    0.06
    ContextProvider
    0.06
    associate
    0.06
     rež
    0.06
     hostilities
    0.06
     लड़ाई
    0.06
    および
    0.06
    ключа
    0.06
    Activations Density 0.010%

    No Known Activations