© 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. 130103
    Prev
    Next
    INDEX
    Explanations

    Mughals, Sultan, Singida, Hyaluronic, Wednesday, Interleukin, Qajar

    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
     ceux
    -0.06
     those
    -0.06
    対応
    -0.06
     would
    -0.06
     najbli
    -0.06
     těch
    -0.06
    𝐄
    -0.06
    ocard
    -0.05
     preterm
    -0.05
    那些
    -0.05
    POSITIVE LOGITS
     استخدم
    0.07
    তারা
    0.06
     разными
    0.06
    ジナ
    0.06
     દરે
    0.06
     শক্তির
    0.06
     restantes
    0.06
    共
    0.06
    حضرت
    0.06
    ंझ
    0.06
    Activations Density 0.007%

    No Known Activations