© 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. 38582
    Prev
    Next
    INDEX
    Explanations

    escape and measurement

    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
    ↵↵
    -1.55
     +"
    -1.53
    their
    -1.48
     ouvido
    -1.44
    estión
    -1.42
     with
    -1.42
     sumber
    -1.41
     stets
    -1.41
    塤
    -1.40
     decisión
    -1.38
    POSITIVE LOGITS
    n
    1.56
    ibile
    1.53
    臜
    1.50
    gencias
    1.48
    ه
    1.48
     desselben
    1.47
    喜歡的
    1.41
    čka
    1.41
    parel
    1.41
    觀眾
    1.39
    Activations Density 0.004%

    No Known Activations