© 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. 82592
    Prev
    Next
    INDEX
    Explanations

    cultural heritage and legacy

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

    The neuron strongly activates on mentions of formal “Cultural Heritage” designations (e.g. “World Cultural Heritage,” “protected heritage,” etc.).

    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
    TypeDef
    -0.76
     fehler
    -0.75
     Structural
    -0.75
     nya
    -0.75
    telijke
    -0.74
     Eats
    -0.73
     Doll
    -0.73
     نویس
    -0.71
     Cao
    -0.71
    PointerException
    -0.71
    POSITIVE LOGITS
     heritage
    3.16
    heritage
    1.92
     Heritage
    1.90
    Heritage
    1.78
     cultural
    1.77
     assets
    1.77
     patrimonio
    1.72
     patrimoine
    1.65
     legacy
    1.61
     treasures
    1.60
    Activations Density 0.028%

    No Known Activations