© 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. 6921
    Prev
    Next
    INDEX
    Explanations

    distillery, dusty, Dusty Baker, AtIndexPath

    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
     This
    -2.61
    yarakat
    -2.36
    饪
    -2.28
    驺
    -2.23
    ໊
    -2.22
    鏐
    -2.19
    櫺
    -2.17
    횃
    -2.17
    änemark
    -2.16
    垍
    -2.16
    POSITIVE LOGITS
    </strong>
    3.41
    .
    3.17
    they
    2.83
            
    2.48
    <em>
    2.34
    <td>
    2.27
    ↵↵
    2.17
    <strong>
    2.13
                  
    2.06
     brist
    1.99
    Activations Density 0.002%

    No Known Activations