© 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. 130316
    Prev
    Next
    INDEX
    Explanations

    performing sectors

    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
    來自
    -0.06
     wildest
    -0.06
     来自
    -0.06
    来自于
    -0.06
     বৈধ
    -0.06
     rookies
    -0.06
     injectable
    -0.05
    leriyle
    -0.05
     dây
    -0.05
     Client
    -0.05
    POSITIVE LOGITS
    webstore
    0.06
    abulary
    0.06
     etwa
    0.06
     hectares
    0.06
     ইতিহাস
    0.06
     पासपोर्ट
    0.06
    ację
    0.06
    ంగా
    0.06
     одному
    0.06
     जरी
    0.06
    Activations Density 0.003%

    No Known Activations