© 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. 130033
    Prev
    Next
    INDEX
    Explanations

    cricket, books, or specific styles

    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
     beautifully
    -0.09
     wonderfully
    -0.08
     brilliantly
    -0.08
     questa
    -0.07
     ....
    -0.07
     acclaimed
    -0.07
     .....
    -0.07
     enormously
    -0.07
     this
    -0.07
     amazing
    -0.07
    POSITIVE LOGITS
     nonlocal
    0.06
    С
    0.06
    であれば
    0.06
    Sean
    0.06
    感觉到
    0.06
    MyAdmin
    0.06
    である
    0.06
     হেতু
    0.06
     شخص
    0.06
     अच्छ
    0.06
    Activations Density 0.004%

    No Known Activations