© 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. 83933
    Prev
    Next
    INDEX
    Explanations

    parks and open spaces

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

    The neuron is detecting mentions of public parks (i.e. the word “park” and closely related park references).

    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
    reton
    -0.94
    ković
    -0.80
     ウール
    -0.80
    eaux
    -0.79
     пъ
    -0.78
    
    -0.78
    bilecek
    -0.78
    NotSupported
    -0.77
    Consent
    -0.77
     Roost
    -0.77
    POSITIVE LOGITS
     parks
    2.41
     park
    2.19
     green
    2.17
    parks
    1.73
    Parks
    1.65
     greens
    1.59
     Parks
    1.54
     spaces
    1.51
    公園
    1.48
     space
    1.45
    Activations Density 0.035%

    No Known Activations