© 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. 106121
    Prev
    Next
    INDEX
    Explanations

    java imports and libraries

    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
     Maastricht
    -0.79
    kuit
    -0.76
     INFIN
    -0.72
    ▋
    -0.72
    hfill
    -0.70
     congen
    -0.70
     Bhattach
    -0.69
     granules
    -0.69
    Editor
    -0.68
    ughty
    -0.68
    POSITIVE LOGITS
     guava
    1.11
     Gu
    0.98
    Gu
    0.97
     collections
    0.91
     Collections
    0.91
     google
    0.90
    google
    0.89
     jersey
    0.81
    Preconditions
    0.79
     collection
    0.78
    Activations Density 0.058%

    No Known Activations