© 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. 38669
    Prev
    Next
    INDEX
    Explanations

    ScrollView, ScrollViewer, ScrollViewers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⢊
    -1.56
    Podemos
    -1.45
    Parece
    -1.41
     preescolar
    -1.38
     them
    -1.33
     guarante
    -1.33
    wardship
    -1.32
    ल्क
    -1.31
     WARN
    -1.31
    EventEmitter
    -1.30
    POSITIVE LOGITS
     can
    1.53
     eset
    1.40
    utentic
    1.38
     Our
    1.37
    怎么回事
    1.36
    鈰
    1.34
     sehr
    1.32
    𓋼
    1.30
    Our
    1.28
     your
    1.27
    Activations Density 0.026%

    No Known Activations