© 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. 15754
    Prev
    Next
    INDEX
    Explanations

    Enron North America Corp

    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
    sistent
    -1.73
    0
    -1.70
     can
    -1.70
    Only
    -1.61
    /**
    -1.52
    writerow
    -1.50
    It
    -1.48
    1
    -1.43
    owę
    -1.41
    For
    -1.40
    POSITIVE LOGITS
     damaligen
    1.98
    ꯷
    1.84
    嫱
    1.82
     zonder
    1.77
    螃
    1.73
     некоторы
    1.73
     Eventually
    1.72
    งิน
    1.69
    衚
    1.69
     Yet
    1.66
    Activations Density 0.035%

    No Known Activations