© 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. 78971
    Prev
    Next
    INDEX
    Explanations

    arts and sciences

    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
     Painters
    -1.13
     PAINTING
    -1.05
     paintings
    -0.97
    Painting
    -0.94
     firft
    -0.92
     Painter
    -0.91
     painter
    -0.91
     Paints
    -0.89
     Painting
    -0.88
     Knife
    -0.87
    POSITIVE LOGITS
     sciences
    1.32
     crafts
    1.27
     Crafts
    1.16
     Sciences
    1.13
     science
    1.05
     humanities
    1.05
     craft
    1.00
     music
    0.99
     letters
    0.98
     culture
    0.98
    Activations Density 0.020%

    No Known Activations