© 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. 45715
    Prev
    Next
    INDEX
    Explanations

    enhanced [descriptor]

    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
    
    -2.17
     thc
    -2.17
    栳
    -2.16
    鏷
    -2.16
     decidedly
    -2.16
     largely
    -2.09
    鑁
    -2.09
     juſt
    -2.03
     delightfully
    -2.02
    拊
    -2.02
    POSITIVE LOGITS
     enhanced
    2.94
    After
    2.81
    While
    2.81
    Even
    2.81
    There
    2.81
    Many
    2.61
    s
    2.58
    _
    2.55
    During
    2.55
    Like
    2.52
    Activations Density 0.009%

    No Known Activations