© 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. 106388
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     sahi
    -0.68
    ulosa
    -0.66
    osexual
    -0.63
    дана
    -0.63
     Buck
    -0.62
     بالإ
    -0.62
    Colo
    -0.62
     buenos
    -0.61
    Consider
    -0.60
     Paw
    -0.60
    POSITIVE LOGITS
    inous
    0.73
    Wars
    0.70
     試験
    0.70
     mobilisation
    0.70
     lilac
    0.69
     Victims
    0.69
    alisasi
    0.69
     reconstituted
    0.68
     coalitions
    0.68
     Voc
    0.67
    Activations Density 0.093%

    No Known Activations