© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72284
    Prev
    Next
    INDEX
    Explanations

    transparent

    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
     The
    -2.86
    莇
    -2.83
    更加
    -2.67
     Therefore
    -2.55
     `
    -2.50
     ine
    -2.48
    蹰
    -2.48
     I
    -2.41
    我不
    -2.41
    -2.36
    POSITIVE LOGITS
    酲
    3.39
    趼
    3.34
    泔
    2.83
    禵
    2.83
    鱘
    2.77
    采用了
    2.75
    下一篇
    2.72
    ︲
    2.70
    屜
    2.64
    ୌ
    2.58
    Activations Density 0.006%

    No Known Activations