© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74524
    Prev
    Next
    INDEX
    Explanations

    motorcycles and their context

    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
     diarios
    -2.08
    遢
    -2.05
    </em>
    -1.91
    ing
    -1.78
    ところは
    -1.73
    
    -1.73
    蒾
    -1.73
     :/
    -1.72
     universitarios
    -1.71
     sanitarias
    -1.68
    POSITIVE LOGITS
     {
    2.03
    ！”
    2.03
    queurs
    2.00
     We
    1.99
    世纪
    1.91
    嵎
    1.90
     飞
    1.85
    ₂)
    1.83
     饭
    1.82
     persino
    1.82
    Activations Density 0.009%

    No Known Activations