© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64188
    Prev
    Next
    INDEX
    Explanations

    CGRect and rectangle definitions

    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
     CGSize
    -0.84
     Stä
    -0.76
     distance
    -0.75
     Glä
    -0.75
    assemb
    -0.74
     distanced
    -0.74
     staff
    -0.73
    ✻
    -0.73
     removed
    -0.72
     distinguir
    -0.71
    POSITIVE LOGITS
    Rect
    1.45
     Rect
    1.38
     rect
    1.38
    rect
    1.27
     bounds
    1.27
    CGRectMake
    1.21
    getBounds
    1.18
     CGRectMake
    1.18
     rectangle
    1.11
     Rectangle
    1.11
    Activations Density 0.029%

    No Known Activations