© 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. 72328
    Prev
    Next
    INDEX
    Explanations

    promoting offers and sales

    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
     there
    -2.14
    When
    -1.99
    There
    -1.98
     There
    -1.94
     When
    -1.91
     only
    -1.75
     it
    -1.74
     Because
    -1.73
    It
    -1.73
    After
    -1.61
    POSITIVE LOGITS
     superbes
    1.77
     magnifiques
    1.72
     REALLY
    1.68
     trám
    1.62
     Dinas
    1.60
     ストライプ
    1.60
     lã
    1.56
     واتس
    1.55
    jedno
    1.49
    "${
    1.48
    Activations Density 0.001%

    No Known Activations