© 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. 117693
    Prev
    Next
    INDEX
    Explanations

    type or kind

    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
     arduous
    -0.06
     Alongside
    -0.06
    不同
    -0.06
     विभिन्न
    -0.06
     sebagai
    -0.06
    贋
    -0.06
    continent
    -0.06
     erode
    -0.06
     Sebagai
    -0.06
     온라인
    -0.06
    POSITIVE LOGITS
    这两个
    0.06
     שי
    0.06
    HERE
    0.06
     esos
    0.06
     उसका
    0.06
     essas
    0.06
    这些
    0.06
     numberOf
    0.06
    urence
    0.06
     wak
    0.05
    Activations Density 0.011%

    No Known Activations