© 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. 26716
    Prev
    Next
    INDEX
    Explanations

    programming code structure

    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
     and
    -1.57
     this
    -1.21
     then
    -1.12
     nothing
    -0.97
    痍
    -0.94
     of
    -0.91
     each
    -0.90
     instead
    -0.87
     their
    -0.85
    一股
    -0.85
    POSITIVE LOGITS
    是我们
    1.08
    hibitor
    1.05
     noci
    1.03
    Dien
    1.03
    そういった
    1.02
    質感
    1.02
    Ár
    1.01
    進化
    0.97
     anunció
    0.96
     ALBERT
    0.95
    Activations Density 0.016%

    No Known Activations