© 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. 128962
    Prev
    Next
    INDEX
    Explanations

    LICENSE or URL

    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
     comunque
    -0.07
     찾아
    -0.06
     identify
    -0.06
     hierarch
    -0.06
     twin
    -0.06
    áu
    -0.06
     gamer
    -0.06
     Akh
    -0.06
    !,
    -0.06
     fict
    -0.06
    POSITIVE LOGITS
     благодаря
    0.07
     overwhelming
    0.06
    使得
    0.06
     సమయంలో
    0.06
     вследствие
    0.06
     עבור
    0.06
     выполнен
    0.06
     باعث
    0.06
     makes
    0.06
     aufgrund
    0.06
    Activations Density 0.003%

    No Known Activations