© 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. 22-GEMMASCOPE-RES-131K
    7. 127813
    Prev
    Next
    INDEX
    Explanations

    class names, variable names

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    来说
    -0.95
     ファイル
    -0.94
     lavabo
    -0.90
    盘
    -0.86
    </em>
    -0.86
     Solidar
    -0.84
     exacerb
    -0.82
    竖
    -0.82
     一起
    -0.81
    Superview
    -0.81
    POSITIVE LOGITS
     detuvo
    0.97
    quear
    0.93
    polate
    0.93
     dokładnie
    0.91
    Makanan
    0.90
     versátil
    0.89
     فقد
    0.89
     ataupun
    0.87
    沿い
    0.87
    &&\
    0.86
    Activations Density 0.003%

    No Known Activations