© 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. 38694
    Prev
    Next
    INDEX
    Explanations

    limited to

    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
     ganska
    -1.77
    ệu
    -1.69
     sokak
    -1.68
     répon
    -1.62
     sabido
    -1.61
    躓
    -1.61
    入った
    -1.60
    :]:
    -1.58
     linkovi
    -1.58
    入り口
    -1.55
    POSITIVE LOGITS
    “
    1.90
    的一切
    1.85
     to
    1.73
    一九
    1.66
     eventuali
    1.66
     serán
    1.62
    ările
    1.58
    一切
    1.55
     haupts
    1.55
     komplette
    1.54
    Activations Density 0.007%

    No Known Activations