© 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. 72528
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
     two
    -1.12
     now
    -1.09
     then
    -1.05
     (
    -1.01
     powietrza
    -0.93
     time
    -0.91
     William
    -0.91
     admittedly
    -0.90
     несмотря
    -0.87
     last
    -0.86
    POSITIVE LOGITS
    ܜ
    1.15
     バッジ
    1.08
     permanentes
    1.06
     yolu
    1.05
     mépris
    1.05
    PARTE
    1.03
     ſi
    1.02
     LATE
    1.01
     relâche
    1.00
     Fußballspieler
    0.99
    Activations Density 0.004%

    No Known Activations