© 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. 118166
    Prev
    Next
    INDEX
    Explanations

    names/titles/urls

    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
     скры
    -0.06
     যাওয়ার
    -0.06
    they
    -0.06
     camouflage
    -0.06
     അവര്‍
    -0.06
     যাবার
    -0.06
     દિવસ
    -0.06
     étudier
    -0.06
     dentro
    -0.06
     kvar
    -0.06
    POSITIVE LOGITS
     Output
    0.06
    ˖
    0.06
     সম্ভবত
    0.06
    集体
    0.06
    可能是
    0.06
     ভো
    0.06
    重大
    0.06
     সংখ্যাল
    0.06
     vergangenen
    0.06
     geliyor
    0.06
    Activations Density 0.003%

    No Known Activations