© 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. 130400
    Prev
    Next
    INDEX
    Explanations

    HTML/XML closing tags

    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
     record
    -0.06
     पहली
    -0.06
     keinen
    -0.06
     первый
    -0.06
     등이
    -0.06
     that
    -0.06
     would
    -0.06
     nenhuma
    -0.06
     libros
    -0.05
     গ্রন্থে
    -0.05
    POSITIVE LOGITS
    ammed
    0.07
     并
    0.06
    mise
    0.06
     Foil
    0.06
     دانست
    0.06
    בוד
    0.06
    くらいの
    0.06
     countering
    0.06
    laştır
    0.06
     MaxPooling
    0.06
    Activations Density 0.003%

    No Known Activations