© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116899
    Prev
    Next
    INDEX
    Explanations

    general aviation aircraft

    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
    eBay
    -0.81
    farers
    -0.75
    HDMI
    -0.75
    Adapters
    -0.74
    utación
    -0.73
    Ax
    -0.73
    Auto
    -0.73
    ±
    -0.73
     ц
    -0.71
    toral
    -0.71
    POSITIVE LOGITS
     aircraft
    2.95
     plane
    2.81
     planes
    2.78
     airplane
    2.75
     airplanes
    2.73
    planes
    2.30
     aeroplane
    2.22
    plane
    2.11
     aviation
    1.98
    PLANE
    1.98
    Activations Density 0.090%

    No Known Activations