© 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. 33574
    Prev
    Next
    INDEX
    Explanations

    circle and circular shapes

    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
    cub
    -0.94
    ARROW
    -0.80
     дов
    -0.79
    浊
    -0.77
    cubes
    -0.75
     வே
    -0.74
    alyptus
    -0.74
     cubes
    -0.74
     Abar
    -0.74
    Cube
    -0.73
    POSITIVE LOGITS
     circle
    3.78
     circular
    3.55
     circles
    3.44
    circle
    3.13
     Circle
    2.98
    circular
    2.95
    Circle
    2.92
    Circular
    2.83
     Circular
    2.80
     círculo
    2.53
    Activations Density 0.083%

    No Known Activations