© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128767
    Prev
    Next
    INDEX
    Explanations

    protease inhibitors or comparisons

    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
    生命
    -0.07
     apprezz
    -0.06
     allows
    -0.06
     umožňuje
    -0.06
    珍惜
    -0.06
     descriptions
    -0.06
     pathway
    -0.05
     describes
    -0.05
     seçenek
    -0.05
     old
    -0.05
    POSITIVE LOGITS
     homemade
    0.07
     forc
    0.06
    💀
    0.06
     न्यायिक
    0.06
     কার্যকর
    0.06
    鷄
    0.06
     іх
    0.06
     маник
    0.06
     বাহিনী
    0.06
     ख
    0.06
    Activations Density 0.005%

    No Known Activations