© 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. 117006
    Prev
    Next
    INDEX
    Explanations

    importance and significance

    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
    惊
    -0.07
    自觉
    -0.07
     répertoire
    -0.06
    enhanced
    -0.06
    inflammatory
    -0.06
    informative
    -0.06
     apprentice
    -0.06
     inflammatory
    -0.06
    部に
    -0.06
     wspól
    -0.06
    POSITIVE LOGITS
    悖
    0.06
     Analytics
    0.06
     dplyr
    0.06
     Pivot
    0.06
    immen
    0.06
    主題
    0.06
     KPMG
    0.06
     ANALYSIS
    0.06
     Deloitte
    0.06
    Câu
    0.06
    Activations Density 0.031%

    No Known Activations