© 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. 60038
    Prev
    Next
    INDEX
    Explanations

    arrows and bows

    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
    iphone
    -0.98
    чего
    -0.79
    🧰
    -0.77
    Unload
    -0.75
     Gust
    -0.73
     Lupin
    -0.73
     تنا
    -0.72
    ’
    -0.71
     gastro
    -0.71
    儺
    -0.71
    POSITIVE LOGITS
     arrow
    1.44
     arrows
    1.39
     archery
    1.36
    箭
    1.19
    arrows
    1.15
     crossbow
    1.14
     archers
    1.04
     Arrows
    1.02
     Archery
    0.98
    矢
    0.94
    Activations Density 0.007%

    No Known Activations