© 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. 6724
    Prev
    Next
    INDEX
    Explanations

    goes beyond or further

    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
     for
    -2.50
     this
    -2.20
     or
    -2.09
     fifteen
    -1.81
     because
    -1.79
    when
    -1.78
     when
    -1.77
     which
    -1.72
     on
    -1.69
     from
    -1.69
    POSITIVE LOGITS
    
    1.99
    絝
    1.90
     FURTHER
    1.84
    苙
    1.83
    𨭎
    1.82
     agres
    1.80
    ？』
    1.78
    翃
    1.77
     tremend
    1.76
     GETTING
    1.75
    Activations Density 0.035%

    No Known Activations