© 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. 128100
    Prev
    Next
    INDEX
    Explanations

    dimensional arrays

    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
    了什么
    -1.79
     lauded
    -1.65
     algunas
    -1.60
     farà
    -1.60
     alcune
    -1.58
     svolge
    -1.54
     imó
    -1.52
     lavora
    -1.52
     algumas
    -1.51
     utilizza
    -1.51
    POSITIVE LOGITS
    愛知
    1.48
    ácií
    1.45
    chukwu
    1.42
     endless
    1.35
     beginnings
    1.30
     bleus
    1.30
    ｗｗｗ
    1.29
     enrollment
    1.28
     regardless
    1.27
     impede
    1.27
    Activations Density 0.035%

    No Known Activations