© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4518
    Prev
    Next
    INDEX
    Explanations

    art mediums and subjects

    np_acts-logits-general · gemini-2.5-flash-lite

    art, painting, murals, digital painting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    攔
    0.55
     뽑
    0.42
    뽑
    0.41
     adenos
    0.41
    椙
    0.41
     தொழி
    0.40
    CTAssert
    0.39
    TextMessage
    0.38
     inoculum
    0.38
    馊
    0.38
    POSITIVE LOGITS
     painting
    3.80
     paintings
    3.41
     Painting
    3.41
    painting
    3.34
    Painting
    3.33
     Paintings
    3.14
     pintura
    3.08
     peinture
    3.06
     painter
    3.02
     pinturas
    3.00
    Activations Density 0.196%

    No Known Activations