© 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. 22-GEMMASCOPE-RES-131K
    7. 72366
    Prev
    Next
    INDEX
    Explanations

    programming language imports

    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
     parfü
    -1.45
     pude
    -1.14
     هذه
    -1.14
     reager
    -1.14
     müh
    -1.12
     Projektu
    -1.11
     beden
    -1.09
    皤
    -1.09
     Snackbar
    -1.08
     parfüm
    -1.07
    POSITIVE LOGITS
     everything
    1.14
     Main
    1.03
     they
    1.02
    あとは
    0.99
    立場
    0.98
    家電
    0.98
    法則
    0.96
     main
    0.95
    でしたが
    0.95
    入り口
    0.94
    Activations Density 0.003%

    No Known Activations