© 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. 62415
    Prev
    Next
    INDEX
    Explanations

    metric measurements

    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
     erkannt
    -0.82
    Comedy
    -0.73
    Inference
    -0.73
     Gabby
    -0.72
     disposi
    -0.71
    ICKNESS
    -0.71
    IGNS
    -0.70
    قة
    -0.69
     Suzy
    -0.69
    主要是
    -0.67
    POSITIVE LOGITS
     metric
    1.19
     $(
    1.13
     }(
    1.05
     Metric
    0.99
     US
    0.97
     cm
    0.92
    metric
    0.88
    Metric
    0.88
    metres
    0.87
    metre
    0.85
    Activations Density 0.069%

    No Known Activations