© 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. 116969
    Prev
    Next
    INDEX
    Explanations

    information and learning

    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
    idders
    -0.06
    বসাইটে
    -0.06
     üç
    -0.06
     mindig
    -0.06
     ویژه
    -0.06
    omerang
    -0.06
    \%)
    -0.06
    encija
    -0.06
    unehm
    -0.06
    বসাইট
    -0.06
    POSITIVE LOGITS
    还
    0.08
     огром
    0.07
     masih
    0.06
     еще
    0.06
    以及
    0.06
    還
    0.06
     still
    0.06
     Mario
    0.06
    তাদের
    0.06
     ‎
    0.06
    Activations Density 0.002%

    No Known Activations