© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107293
    Prev
    Next
    INDEX
    Explanations

    museums and exhibitions

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

    The neuron strongly activates on proper-noun museum and gallery names (e.g. Science Museum, Wonderlab, Equinor Gallery) as they appear in section headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Museums
    -0.95
     museums
    -0.88
     pasaron
    -0.77
    ubro
    -0.75
     SNA
    -0.75
    Inspec
    -0.73
    Regi
    -0.73
     Warlock
    -0.73
     afield
    -0.72
    Astronom
    -0.72
    POSITIVE LOGITS
     galleries
    2.42
     gallery
    1.92
     exhibit
    1.83
     exhibits
    1.75
     Galleries
    1.58
     exhibition
    1.52
     Gallery
    1.51
    gallery
    1.48
    Gallery
    1.45
     exhibitions
    1.43
    Activations Density 0.025%

    No Known Activations