© 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. 79204
    Prev
    Next
    INDEX
    Explanations

    edit links and GET requests

    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
    Not in Any Lists

    No Comments

    Negative Logits
     width
    -0.90
    atán
    -0.86
     Overview
    -0.86
     Tiene
    -0.84
     има
    -0.82
    𝑵
    -0.82
     tener
    -0.80
     Used
    -0.79
     where
    -0.79
     luta
    -0.79
    POSITIVE LOGITS
     jų
    0.83
     vandens
    0.79
    DTOs
    0.79
     соответствует
    0.79
    Bli
    0.78
     όμως
    0.77
     맞
    0.76
     vectorstock
    0.76
     वाल
    0.75
    legungen
    0.75
    Activations Density 0.010%

    No Known Activations