© 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. 79341
    Prev
    Next
    INDEX
    Explanations

    aba, iba, ba

    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
     рассказывает
    -0.72
    contributors
    -0.69
    當初
    -0.69
     туда
    -0.69
     involves
    -0.69
     Af
    -0.68
     фі
    -0.67
    Життє
    -0.67
    SelectedItem
    -0.66
    搶
    -0.66
    POSITIVE LOGITS
    ergic
    0.85
    eren
    0.79
     parma
    0.78
    σι
    0.77
    damente
    0.74
     fakta
    0.73
     anciens
    0.73
    erent
    0.73
    bav
    0.73
     awesome
    0.73
    Activations Density 0.030%

    No Known Activations