© 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. 79392
    Prev
    Next
    INDEX
    Explanations

    type="

    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
     congre
    -0.79
     creciendo
    -0.78
    anello
    -0.77
    还真
    -0.76
    不敢
    -0.75
     inmig
    -0.74
     Sơ
    -0.73
    拣
    -0.73
    喜んで
    -0.73
     Deity
    -0.72
    POSITIVE LOGITS
     サンダル
    0.90
    ֵ
    0.85
    gaven
    0.82
     läh
    0.81
    gulier
    0.81
    ständen
    0.80
    zew
    0.80
    族館
    0.80
    gangss
    0.78
     rojos
    0.78
    Activations Density 0.006%

    No Known Activations