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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7503
    Prev
    Next
    INDEX
    Explanations

    computer and card games

    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
     yesterday
    -1.48
     what
    -1.42
     previously
    -1.37
     that
    -1.36
     today
    -1.32
     уже
    -1.29
     through
    -1.28
    说
    -1.27
     thus
    -1.23
     którzy
    -1.23
    POSITIVE LOGITS
     parfums
    1.54
    Другие
    1.50
     kapag
    1.46
     constater
    1.45
     Prefeitura
    1.44
     marinho
    1.42
     acus
    1.38
     appartement
    1.38
     varje
    1.36
     talaga
    1.35
    Activations Density 0.359%

    No Known Activations