© 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. 117320
    Prev
    Next
    INDEX
    Explanations

    days of the week, names, French terms

    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
     nowych
    -0.06
     polymerase
    -0.06
     novos
    -0.06
    Only
    -0.06
     dzi
    -0.06
     only
    -0.06
     chứ
    -0.06
     മാത്രമേ
    -0.05
     அன்று
    -0.05
     seules
    -0.05
    POSITIVE LOGITS
     اکثر
    0.08
     большин
    0.07
    ඇ
    0.07
     certain
    0.06
     ज्यादातर
    0.06
    大多数
    0.06
     sixteen
    0.06
     कथित
    0.06
     έχει
    0.06
     බොහෝ
    0.06
    Activations Density 0.001%

    No Known Activations