© 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. 116362
    Prev
    Next
    INDEX
    Explanations

    international context or locations

    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
    渶
    -0.07
    日本語
    -0.07
     inglesa
    -0.06
    ுகளை
    -0.06
    鹿児
    -0.06
    কেলে
    -0.06
    πί
    -0.06
     ала
    -0.06
    ギリ
    -0.06
     Florida
    -0.06
    POSITIVE LOGITS
     veřej
    0.06
     सहानुभूति
    0.06
    visually
    0.06
     Verlust
    0.06
     bijvoorbeeld
    0.06
     সাধারণভাবে
    0.06
     October
    0.05
     સમગ્ર
    0.05
     serializers
    0.05
    dafx
    0.05
    Activations Density 0.016%

    No Known Activations