© 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. 130984
    Prev
    Next
    INDEX
    Explanations

    main activity or starting point

    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
     Walt
    -0.06
     सहित
    -0.06
    peu
    -0.06
    水源
    -0.06
     কৃত
    -0.06
     дополнительных
    -0.06
    至於
    -0.06
    ～～
    -0.06
    やり
    -0.06
     بمعنى
    -0.06
    POSITIVE LOGITS
     would
    0.07
    各个
    0.06
    新たに
    0.06
     वेगवेगळ्या
    0.06
     Semua
    0.06
     constructively
    0.06
     strangled
    0.06
    この
    0.06
    各大
    0.06
     newly
    0.06
    Activations Density 0.002%

    No Known Activations