© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    choosing options or items

    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
    ↵
    -2.03
     …”
    -1.77
    ”（
    -1.72
    </strong>
    -1.70
    !”
    -1.70
    …”
    -1.69
    ,”
    -1.67
    日の
    -1.60
    。”
    -1.59
     Londra
    -1.57
    POSITIVE LOGITS
     beijo
    1.84
    迓
    1.84
     abraço
    1.81
    ༛
    1.80
    噲
    1.79
     ส์
    1.71
     his
    1.70
    厹
    1.69
     wisely
    1.69
    chose
    1.66
    Activations Density 0.099%

    No Known Activations