© 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. 128922
    Prev
    Next
    INDEX
    Explanations

    numbered list item markers

    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
     větš
    -0.08
     normalmente
    -0.07
     обычно
    -0.07
     normally
    -0.07
     normalerweise
    -0.07
     einem
    -0.07
    więks
    -0.07
     normalement
    -0.06
     ஒரு
    -0.06
     اكثر
    -0.06
    POSITIVE LOGITS
    답니다
    0.06
     comprehensively
    0.06
     պատ
    0.06
    深夜
    0.06
     বেঁ
    0.05
     প্রেসক্লাবের
    0.05
     হাস্য
    0.05
     pleasantly
    0.05
     addirittura
    0.05
     refrained
    0.05
    Activations Density 0.001%

    No Known Activations