© 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. 25181
    Prev
    Next
    INDEX
    Explanations

    ```dots, parentheses, and code syntax```

    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
    Not in Any Lists

    No Comments

    Negative Logits
     If
    -1.05
    ៈ
    -1.02
    ઃ
    -0.99
    本当
    -0.96
     istnieje
    -0.96
     that
    -0.95
     个性
    -0.95
     where
    -0.93
     everything
    -0.93
    Where
    -0.93
    POSITIVE LOGITS
     бывают
    0.98
     måned
    0.94
     گی
    0.92
    但是在
    0.91
    .@
    0.90
     kindled
    0.90
     nieuwe
    0.90
     mới
    0.89
    ęt
    0.89
    着一个
    0.89
    Activations Density 0.007%

    No Known Activations