© 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. 66361
    Prev
    Next
    INDEX
    Explanations

    sliding French doors

    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
     vitale
    -0.81
    Equals
    -0.79
    dentro
    -0.79
     mencu
    -0.75
    Janet
    -0.74
     disfraz
    -0.74
     donker
    -0.74
    gste
    -0.74
    Заключение
    -0.73
    getSingle
    -0.73
    POSITIVE LOGITS
     doors
    2.47
     sliding
    2.03
     French
    1.95
     Doors
    1.82
    Doors
    1.75
     french
    1.73
     door
    1.67
     Sliding
    1.62
    French
    1.60
    Sliding
    1.55
    Activations Density 0.009%

    No Known Activations