© 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. 10-GEMMASCOPE-RES-131K
    7. 72158
    Prev
    Next
    INDEX
    Explanations

    MIT and Apache licenses

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    primarily
    -1.89
    mainly
    -1.85
     [
    -1.79
    -
    -1.66
    y
    -1.63
    f
    -1.61
    p
    -1.52
    ḿ
    -1.42
     usando
    -1.41
    referred
    -1.41
    POSITIVE LOGITS
    eadilan
    1.73
     EconPapers
    1.50
    pAd
    1.47
    胫
    1.46
    rédients
    1.45
    Enllaces
    1.45
    ゐ
    1.43
    gæ
    1.43
    cestry
    1.42
     poignant
    1.41
    Activations Density 0.396%

    No Known Activations