© 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. 10-GEMMASCOPE-RES-131K
    4. 9808
    Prev
    Next
    INDEX
    Explanations

    world heritage sites

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

    The neuron detects mentions of UNESCO World Heritage (or tentative) listings and related heritage designation terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    München
    -1.72
    Köln
    -1.68
    釭
    -1.66
    Sementara
    -1.59
    骉
    -1.56
     grotte
    -1.52
     inond
    -1.52
     dà
    -1.49
    chefs
    -1.48
    琹
    -1.48
    POSITIVE LOGITS
     it
    1.77
     "
    1.45
    :
    1.38
    </strong>
    1.38
     deba
    1.28
    k
    1.28
     however
    1.27
     ويمكن
    1.26
     ''
    1.25
    を経
    1.25
    Activations Density 0.005%

    No Known Activations