© 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. 38466
    Prev
    Next
    INDEX
    Explanations

    places or systems operated/maintained

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

    This neuron fires on the “defining” noun phrases in sentences of the form “X is a Y,” picking out the type term (e.g. station, road, park, cemetery, event) that immediately follows the copula.

    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
    vetti
    -0.87
     przewod
    -0.87
    StringValue
    -0.86
     Gehalt
    -0.82
     szkoły
    -0.81
    innan
    -0.80
    enciais
    -0.79
     wykorzyst
    -0.78
     wraz
    -0.78
    跄
    -0.77
    POSITIVE LOGITS
     owned
    3.83
     operated
    3.61
     administered
    2.83
    operated
    2.78
    owned
    2.73
    Owned
    2.73
     managed
    2.72
     Owned
    2.69
     maintained
    2.64
     Operated
    2.59
    Activations Density 0.245%

    No Known Activations