© 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. 34-GEMMASCOPE-RES-131K
    7. 108692
    Prev
    Next
    INDEX
    Explanations

    ornate, gilded, and antique styles

    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
    bảng
    -0.91
    誒
    -0.88
     púb
    -0.84
    倆
    -0.84
    飄
    -0.83
    てて
    -0.83
    کنون
    -0.82
    Variante
    -0.82
     Stonehenge
    -0.82
     =>'
    -0.81
    POSITIVE LOGITS
     gold
    1.73
    gold
    1.42
     ornate
    1.34
     gilded
    1.32
     marble
    1.32
     Victorian
    1.30
     gilt
    1.23
     floral
    1.21
     antique
    1.20
     golden
    1.16
    Activations Density 0.041%

    No Known Activations