© 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. 83632
    Prev
    Next
    INDEX
    Explanations

    anything nothing something else

    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
    Negative Logits
    ㍑
    -2.20
    
    -1.91
     également
    -1.87
     uly
    -1.81
     نیز
    -1.79
     短发
    -1.77
     umid
    -1.77
     -------
    -1.76
    
    -1.76
    ープン
    -1.71
    POSITIVE LOGITS
     a
    2.06
    )
    1.98
    </strong>
    1.73
     everybody
    1.66
     When
    1.63
    ).
    1.63
     else
    1.62
     everyone
    1.59
     «
    1.57
    してみた
    1.54
    Activations Density 0.049%

    No Known Activations