© 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. 10-GEMMASCOPE-RES-131K
    7. 101547
    Prev
    Next
    INDEX
    Explanations

    sports events and athletes

    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_10/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
     you
    -1.35
    How
    -1.28
     sartén
    -1.25
    一楼
    -1.23
     decreto
    -1.20
    好きです
    -1.20
     другим
    -1.20
     {
    -1.19
     [];
    -1.16
     other
    -1.15
    POSITIVE LOGITS
    िटी
    1.39
     知道
    1.31
    ScopeManager
    1.28
    UCIÓN
    1.26
     Corbu
    1.25
    罘
    1.25
    ekwondo
    1.24
    they
    1.24
    mang
    1.23
    tellers
    1.23
    Activations Density 0.079%

    No Known Activations