© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130993
    Prev
    Next
    INDEX
    Explanations

    US research plan committee

    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
    гляд
    -0.07
    นี้
    -0.06
    optimal
    -0.06
    ，
    -0.06
     Chandigarh
    -0.06
     Nairobi
    -0.06
     testo
    -0.05
     ভাঙ্গ
    -0.05
     بلوچستان
    -0.05
     Komb
    -0.05
    POSITIVE LOGITS
     বিরাট
    0.07
     stockholders
    0.07
     overhang
    0.07
     stockholder
    0.06
     shareholders
    0.06
     influencer
    0.06
     تبقى
    0.06
     чуть
    0.06
     американ
    0.06
     గవర్
    0.06
    Activations Density 0.003%

    No Known Activations