© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25655
    Prev
    Next
    INDEX
    Explanations

    art and historical objects

    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
    遗产
    -0.84
     скла
    -0.78
    listBox
    -0.77
    博物館
    -0.77
     content
    -0.77
     یا
    -0.76
     incluso
    -0.76
    Maybe
    -0.75
     analysis
    -0.73
    oflu
    -0.73
    POSITIVE LOGITS
     prints
    1.04
     medieval
    1.02
     objet
    1.00
     objets
    1.00
     artifacts
    0.99
     ancient
    0.99
     objects
    0.99
    Ран
    0.98
    prints
    0.96
     European
    0.95
    Activations Density 0.029%

    No Known Activations