© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21298
    Prev
    Next
    INDEX
    Explanations

    art and artistic expression

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

    art and creation

    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_31_width_262k_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
    ع
    0.90
    N
    0.76
    ü
    0.75
    U
    0.73
    م
    0.71
    at
    0.69
    ת
    0.64
     diagn
    0.63
     trusty
    0.63
    V
    0.63
    POSITIVE LOGITS
    Artista
    0.81
    アート
    0.79
     искусства
    0.79
     예술
    0.75
     art
    0.72
     インテリア
    0.71
     artisti
    0.71
     미술
    0.71
     artistas
    0.69
    artista
    0.69
    Activations Density 0.074%

    No Known Activations