© 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. 72364
    Prev
    Next
    INDEX
    Explanations

    references and links

    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
     Some
    -2.02
     Two
    -1.84
     When
    -1.83
     semblables
    -1.77
    𓍊
    -1.76
    地说
    -1.74
     attravers
    -1.73
    .
    -1.68
     удовольствием
    -1.68
     Following
    -1.68
    POSITIVE LOGITS
     essas
    1.87
     in
    1.84
     astute
    1.80
    ᨘ
    1.78
     prakty
    1.75
    碾
    1.74
     GETTING
    1.71
    
    1.66
     AUTOMATIC
    1.66
     OTHERWISE
    1.65
    Activations Density 0.024%

    No Known Activations