© 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. 10-GEMMASCOPE-RES-131K
    7. 42349
    Prev
    Next
    INDEX
    Explanations

    installing packages or running code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -1.76
     lorsque
    -1.67
    hline
    -1.60
     who
    -1.45
     whom
    -1.38
    需要
    -1.33
     نیز
    -1.31
     lorsqu
    -1.30
     που
    -1.30
     когда
    -1.30
    POSITIVE LOGITS
     about
    2.03
     or
    1.72
    ského
    1.58
     at
    1.58
    喩
    1.38
     again
    1.34
    atchewan
    1.33
     first
    1.30
     today
    1.29
    ācija
    1.23
    Activations Density 0.110%

    No Known Activations