© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130218
    Prev
    Next
    INDEX
    Explanations

    code import statements or comments

    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
    㖡
    -0.06
     Вер
    -0.06
     wówczas
    -0.06
     for
    -0.06
    Вер
    -0.06
    이면
    -0.06
     papp
    -0.06
     proving
    -0.06
     খালেদা
    -0.06
    iferous
    -0.05
    POSITIVE LOGITS
    ཐ
    0.06
     দেখলেন
    0.06
    hotmail
    0.06
    performance
    0.06
     এখানে
    0.06
     ന്
    0.06
    线条
    0.06
     unorthodox
    0.06
     refurbished
    0.05
     Addition
    0.05
    Activations Density 0.005%

    No Known Activations