© 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. 119513
    Prev
    Next
    INDEX
    Explanations

    version page home daily here flowers

    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
     sản
    -0.07
     produced
    -0.07
    getInput
    -0.07
     displaying
    -0.06
     was
    -0.06
     нём
    -0.06
     intimately
    -0.06
     موسي
    -0.06
     খেলোয়া
    -0.06
     খেলার
    -0.06
    POSITIVE LOGITS
     world
    0.06
    一天
    0.06
     و
    0.06
     عالمی
    0.06
     Fact
    0.06
    だけ
    0.06
    世界
    0.06
     datap
    0.06
     আমিন
    0.05
     todo
    0.05
    Activations Density 0.002%

    No Known Activations