© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81008
    Prev
    Next
    INDEX
    Explanations

    common code abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     one
    -1.50
     like
    -1.23
     what
    -1.03
     with
    -1.01
     in
    -0.99
     that
    -0.97
     around
    -0.96
     therefore
    -0.96
     people
    -0.94
     but
    -0.92
    POSITIVE LOGITS
    sikan
    1.03
    λι
    1.02
    primarily
    1.01
     takich
    1.01
     mépris
    1.00
     permanentes
    0.98
     iNdEx
    0.97
    鹚
    0.97
    without
    0.96
     arriver
    0.96
    Activations Density 0.037%

    No Known Activations