© 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. 119090
    Prev
    Next
    INDEX
    Explanations

    seasons of the year

    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
     month
    -0.07
     mensuales
    -0.06
     certainly
    -0.06
    MONTH
    -0.06
    ㅐ
    -0.06
     Month
    -0.06
     ebenso
    -0.06
    tw
    -0.06
    Month
    -0.06
     miesią
    -0.06
    POSITIVE LOGITS
     문제입니다
    0.07
     ಹೊಸ
    0.06
     mà
    0.06
     exhilar
    0.06
     новых
    0.06
     ogn
    0.06
     إلى
    0.06
     Ausgang
    0.06
     interf
    0.06
     कुंजी
    0.06
    Activations Density 0.007%

    No Known Activations