© 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. 118508
    Prev
    Next
    INDEX
    Explanations

    docker programming and research terms

    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
     devez
    -0.06
     risque
    -0.06
     doivent
    -0.06
     चाहि
    -0.06
    peak
    -0.06
     vrchol
    -0.06
    원본
    -0.06
    लाइड
    -0.05
     BEGIN
    -0.05
    最初の
    -0.05
    POSITIVE LOGITS
    пова
    0.06
     समुद्री
    0.06
     ყველა
    0.06
     international
    0.06
     internazionale
    0.06
    Buttons
    0.06
    نيف
    0.06
     hầu
    0.06
     அனைத்து
    0.06
    の方
    0.06
    Activations Density 0.007%

    No Known Activations