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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65317
    Prev
    Next
    INDEX
    Explanations

    sports field markings

    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_34/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
     Wiktionnaire
    -0.92
     عبر
    -0.83
    AllowAnonymous
    -0.80
    ⒉
    -0.78
    ciera
    -0.76
    ekwondo
    -0.75
    ǿ
    -0.75
    assies
    -0.74
    xB
    -0.72
    >",
    -0.72
    POSITIVE LOGITS
     circle
    1.34
     circles
    1.21
     markings
    1.13
     area
    1.13
     box
    1.10
     arc
    1.09
     lines
    1.08
     hash
    1.06
     restraining
    1.04
     Boxes
    1.02
    Activations Density 0.013%

    No Known Activations