© 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. 79360
    Prev
    Next
    INDEX
    Explanations

    weeks later

    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
    ترل
    -0.73
    rss
    -0.72
    簷
    -0.71
    īts
    -0.71
     Республи
    -0.70
     underlined
    -0.70
    Miri
    -0.70
    重的
    -0.70
     Multiplex
    -0.69
    UTRAL
    -0.69
    POSITIVE LOGITS
    YAN
    1.16
     place
    0.95
    Place
    0.87
    <strong>
    0.85
    Yan
    0.84
    place
    0.81
    www
    0.80
     pesan
    0.78
     www
    0.78
    boards
    0.77
    Activations Density 0.012%

    No Known Activations