© 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. 116946
    Prev
    Next
    INDEX
    Explanations

    Bruce Arians

    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
    名称
    -0.06
    ണ്ഡ
    -0.06
    表現
    -0.06
     название
    -0.06
     characterize
    -0.06
    どもの
    -0.06
     often
    -0.06
     informative
    -0.06
     name
    -0.06
     выражение
    -0.06
    POSITIVE LOGITS
    бран
    0.06
     restlessness
    0.06
     سب
    0.06
     senere
    0.06
     السوق
    0.05
    ablus
    0.05
     Subsequent
    0.05
    Inclusive
    0.05
     antic
    0.05
    los
    0.05
    Activations Density 0.001%

    No Known Activations