© 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. 98855
    Prev
    Next
    INDEX
    Explanations

    2x, -way, /

    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
    .
    -1.76
     
    -1.58
    !
    -1.51
     kedua
    -1.49
    тят
    -1.48
     dazzling
    -1.45
    讃
    -1.41
     it
    -1.41
    </h4>
    -1.37
    <sup>
    -1.37
    POSITIVE LOGITS
     ſou
    1.98
     lampada
    1.74
     étrang
    1.73
     of
    1.72
     cérami
    1.71
    嫆
    1.70
     purpoſe
    1.68
    mored
    1.64
    AddHtmlAttribute
    1.63
    
    1.60
    Activations Density 0.019%

    No Known Activations