© 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. 130523
    Prev
    Next
    INDEX
    Explanations

    questions and other languages

    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
               
    -0.06
    ありますが
    -0.05
     set
    -0.05
     آنچه
    -0.05
    check
    -0.05
    仅
    -0.05
    先
    -0.05
     παρέ
    -0.05
     solely
    -0.05
     within
    -0.05
    POSITIVE LOGITS
    他の
    0.08
     otra
    0.07
     adventurous
    0.07
     अगले
    0.07
     aventura
    0.07
     altri
    0.07
    相关的
    0.06
     enhances
    0.06
     other
    0.06
     reckless
    0.06
    Activations Density 0.005%

    No Known Activations