© 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. 34-GEMMASCOPE-RES-131K
    7. 29921
    Prev
    Next
    INDEX
    Explanations

    JPEG compression quality

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    chaffung
    -0.78
     Reinigung
    -0.78
     diversas
    -0.76
     videos
    -0.76
    anco
    -0.75
     foreigner
    -0.73
     Buche
    -0.72
    kuper
    -0.72
     able
    -0.71
    TimeoutException
    -0.70
    POSITIVE LOGITS
     compression
    1.70
     JPEG
    1.60
    JPEG
    1.54
    compression
    1.52
     quality
    1.48
    Compression
    1.44
     Compression
    1.41
    quality
    1.41
    Quality
    1.37
    QUALITY
    1.33
    Activations Density 0.016%

    No Known Activations