© 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. 119837
    Prev
    Next
    INDEX
    Explanations

    Galera, Software Foundation, Rough Trade, Jeanette

    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
    Also
    -0.07
     کودکان
    -0.06
    Target
    -0.06
    휼
    -0.06
    ատ
    -0.06
     charity
    -0.06
     الأطفال
    -0.06
     물론
    -0.05
    뭘
    -0.05
    ২
    -0.05
    POSITIVE LOGITS
     exib
    0.06
     мг
    0.06
     circol
    0.06
     leden
    0.06
    回避
    0.06
     behaupt
    0.06
     harmonious
    0.06
    .*;
    0.05
    utral
    0.05
     Horizontal
    0.05
    Activations Density 0.001%

    No Known Activations