© 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. 22-GEMMASCOPE-RES-131K
    7. 32851
    Prev
    Next
    INDEX
    Explanations

    document structure labels and code

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     first
    -1.33
    .......
    -1.31
     Getting
    -1.29
     getting
    -1.27
     gets
    -1.27
    ......
    -1.22
     just
    -1.20
     Despite
    -1.19
     people
    -1.18
    !!!
    -1.18
    POSITIVE LOGITS
    
    1.41
    隳
    1.41
    quels
    1.40
    comme
    1.38
     soooo
    1.36
     boute
    1.34
    傒
    1.34
     reutiliz
    1.34
     rése
    1.33
     niedersachsen
    1.32
    Activations Density 0.051%

    No Known Activations