© 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. 106543
    Prev
    Next
    INDEX
    Explanations

    painted objects and art

    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
    Streets
    -0.93
     paroisse
    -0.84
    gridColumn
    -0.83
     Stack
    -0.82
    Sculpture
    -0.82
    Emissions
    -0.81
     ľah
    -0.77
    Stacks
    -0.76
    rašymas
    -0.75
    screenshots
    -0.73
    POSITIVE LOGITS
     mural
    1.91
     painting
    1.80
     murals
    1.79
     painted
    1.74
     wall
    1.66
     paintings
    1.64
     paint
    1.49
     fresco
    1.49
    mural
    1.48
     ceiling
    1.46
    Activations Density 0.017%

    No Known Activations