© 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. 34-GEMMASCOPE-RES-131K
    7. 47031
    Prev
    Next
    INDEX
    Explanations

    date ranges and years

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     quickly
    -0.79
     rapidly
    -0.78
    ricate
    -0.78
    ثي
    -0.73
     sixty
    -0.72
     perhaps
    -0.71
    قرأ
    -0.70
     sadly
    -0.70
     utilizó
    -0.69
    取締役
    -0.68
    POSITIVE LOGITS
     turn
    1.37
     Jahrhundert
    1.00
    Turn
    0.94
    hundreds
    0.92
     siècle
    0.90
    Century
    0.90
     Turn
    0.88
     Century
    0.84
     TURN
    0.82
     Ş
    0.79
    Activations Density 0.030%

    No Known Activations