© 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. 117931
    Prev
    Next
    INDEX
    Explanations

    file, Php, content, daemon

    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
     à
    -0.06
     역할
    -0.06
     জার্মান
    -0.06
     see
    -0.06
    中有
    -0.06
    essayer
    -0.06
     അഭ
    -0.06
     encontrarás
    -0.06
     करण्यासाठी
    -0.06
    칙
    -0.06
    POSITIVE LOGITS
     باعث
    0.07
     बढ़ाता
    0.06
    由此
    0.06
     Todos
    0.06
    सभी
    0.06
     يجعل
    0.06
     этого
    0.06
    eries
    0.05
    Possibly
    0.05
    是将
    0.05
    Activations Density 0.001%

    No Known Activations