© 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. 22-GEMMASCOPE-RES-131K
    7. 25236
    Prev
    Next
    INDEX
    Explanations

    listing similar groups

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}"></
    -0.93
    bihan
    -0.92
    に行って
    -0.87
     Aujourd
    -0.84
     když
    -0.84
     brunt
    -0.81
     "¿
    -0.80
     rootView
    -0.79
    に行った
    -0.79
    vtk
    -0.79
    POSITIVE LOGITS
     likewise
    1.21
    同じく
    0.97
     meanwhile
    0.97
     also
    0.97
     Likewise
    0.96
    氛
    0.90
     كذلك
    0.89
     ditto
    0.88
     similarly
    0.87
    もあります
    0.87
    Activations Density 0.105%

    No Known Activations