© 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. 117053
    Prev
    Next
    INDEX
    Explanations

    products, pricing, selected

    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
     helps
    -0.07
     holy
    -0.06
     وغ
    -0.06
     Endocrinol
    -0.06
     помогают
    -0.06
     ajudar
    -0.06
     для
    -0.06
    んだけど
    -0.06
     uphill
    -0.06
    坷
    -0.06
    POSITIVE LOGITS
     products
    0.07
    產品
    0.06
     selected
    0.06
    selected
    0.06
     SELECTED
    0.06
    products
    0.06
    定价
    0.06
     продукты
    0.06
     Selected
    0.06
     prijs
    0.06
    Activations Density 0.003%

    No Known Activations