© 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. 118889
    Prev
    Next
    INDEX
    Explanations

    delete item

    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
     eram
    -0.06
     vanwege
    -0.06
     would
    -0.06
     इंजन
    -0.06
    跟踪
    -0.06
     চল্লিশ
    -0.06
     üzer
    -0.06
     tracking
    -0.06
     প্রতিবেশী
    -0.06
    Pergunta
    -0.05
    POSITIVE LOGITS
    BY
    0.07
     التي
    0.06
     what
    0.06
     wirtschaft
    0.06
     पासवर्ड
    0.06
     високо
    0.06
     boj
    0.06
     που
    0.06
    શા
    0.06
     què
    0.06
    Activations Density 0.001%

    No Known Activations