© 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. 84689
    Prev
    Next
    INDEX
    Explanations

    museum collections and admissions

    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
    iettes
    -0.88
     Pareto
    -0.79
    arbon
    -0.79
     nove
    -0.77
    ucle
    -0.76
    crest
    -0.75
    さみ
    -0.75
    :'#
    -0.75
    leans
    -0.74
    rimid
    -0.74
    POSITIVE LOGITS
     museum
    1.77
     visitors
    1.52
     Museum
    1.52
    Museum
    1.44
    Visitors
    1.34
     visitor
    1.32
     Members
    1.29
    museum
    1.23
     Visitor
    1.22
     visitantes
    1.20
    Activations Density 0.034%

    No Known Activations