© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102773
    Prev
    Next
    INDEX
    Explanations

    ceremonial parade or act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    遢
    -2.52
    f
    -2.14
     and
    -2.03
    Z
    -1.98
     Դ
    -1.96
     excruciating
    -1.96
    膛
    -1.95
    慊
    -1.95
    
    -1.88
    AL
    -1.87
    POSITIVE LOGITS
    癀
    2.67
     the
    2.44
    塒
    2.14
    狴
    2.09
    を出す
    2.09
     
    2.03
    蛲
    2.02
    壜
    1.98
    𝙜
    1.98
    вгений
    1.98
    Activations Density 0.002%

    No Known Activations