© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118048
    Prev
    Next
    INDEX
    Explanations

    aviation

    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
     jotka
    -0.07
     که
    -0.06
     którzy
    -0.06
     التي
    -0.06
     experiencing
    -0.06
     fazla
    -0.06
     التى
    -0.06
     ที
    -0.06
     আজকে
    -0.06
     which
    -0.06
    POSITIVE LOGITS
     it
    0.08
     либо
    0.06
     THERE
    0.06
     lehető
    0.06
     memungkinkan
    0.06
     verdiği
    0.06
     ĝi
    0.06
    表示
    0.06
     значительно
    0.06
     might
    0.06
    Activations Density 0.031%

    No Known Activations