© 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. 129124
    Prev
    Next
    INDEX
    Explanations

    querying data or lists

    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
     bunların
    -0.06
    SPECIAL
    -0.06
    এবং
    -0.06
     your
    -0.06
     the
    -0.06
     diejenigen
    -0.06
     όπου
    -0.06
    ركات
    -0.06
     отсут
    -0.06
    There
    -0.06
    POSITIVE LOGITS
     new
    0.07
    新
    0.06
     ಅಥವಾ
    0.06
     Ibadan
    0.06
     restre
    0.06
    দান
    0.06
    ط
    0.06
    ₂,
    0.06
    遂
    0.06
    elfde
    0.06
    Activations Density 0.141%

    No Known Activations