© 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. 129103
    Prev
    Next
    INDEX
    Explanations

    Japan Airlines Co. led

    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
     ఇదే
    -0.07
    撷
    -0.06
     this
    -0.06
    Deze
    -0.06
     ফুটে
    -0.06
     학교
    -0.06
     occurring
    -0.06
    امت
    -0.06
     الاختبار
    -0.06
     aliqu
    -0.06
    POSITIVE LOGITS
     likeness
    0.06
     sleepy
    0.06
     API
    0.06
    之外
    0.05
     complete
    0.05
    ことにより
    0.05
    APP
    0.05
     software
    0.05
     ऐप्प
    0.05
     থাকবেন
    0.05
    Activations Density 0.001%

    No Known Activations