© 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. 117489
    Prev
    Next
    INDEX
    Explanations

    our possession or association

    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
     ensuring
    -0.07
     ensured
    -0.06
     পাকিস্তানী
    -0.06
    zahlung
    -0.06
     either
    -0.06
     stuff
    -0.06
    fixing
    -0.06
     الحاس
    -0.06
    保证
    -0.06
    ógł
    -0.06
    POSITIVE LOGITS
    我們
    0.08
    我们
    0.08
     nossa
    0.07
    在我们
    0.07
     我们
    0.07
     우리
    0.07
     nuestros
    0.07
     нами
    0.07
     our
    0.06
     μας
    0.06
    Activations Density 0.009%

    No Known Activations