© 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. 119272
    Prev
    Next
    INDEX
    Explanations

    reviews, feedback, opinions

    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
    各项
    -0.07
     available
    -0.06
     efficace
    -0.06
    Available
    -0.06
     všechny
    -0.06
     irgendwo
    -0.06
    Ingredients
    -0.06
    分析
    -0.06
    最佳
    -0.06
     escrit
    -0.06
    POSITIVE LOGITS
    participation
    0.06
    妆
    0.06
     friendships
    0.06
     frustrations
    0.06
    ciphertext
    0.06
    变成了
    0.06
     facilitation
    0.05
    不满
    0.05
     dealt
    0.05
     participation
    0.05
    Activations Density 0.003%

    No Known Activations