© 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. 118023
    Prev
    Next
    INDEX
    Explanations

    Beb

    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
     physician
    -0.07
     new
    -0.07
    医師
    -0.06
     обоих
    -0.06
     custo
    -0.06
     nieuwe
    -0.06
    塩
    -0.06
     ঝুঁক
    -0.06
    كما
    -0.06
     indian
    -0.06
    POSITIVE LOGITS
     สามารถ
    0.06
     นึง
    0.06
     can
    0.06
    Wing
    0.06
     sees
    0.05
     नांद
    0.05
    KH
    0.05
    หนึ่ง
    0.05
     see
    0.05
    購買
    0.05
    Activations Density 0.008%

    No Known Activations