© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59546
    Prev
    Next
    INDEX
    Explanations

    historic buildings and districts

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

    The neuron detects mentions of “historic” or “old” in the context of heritage sites, buildings, or preservation.

    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
     nuevos
    -0.82
    Ỉ
    -0.82
    なので
    -0.81
    ઃ
    -0.81
     кроме
    -0.79
    舐
    -0.79
     nuevas
    -0.78
     liczby
    -0.77
     herói
    -0.76
    让自己
    -0.76
    POSITIVE LOGITS
     buildings
    1.21
     railway
    1.13
     structures
    1.11
     railroad
    1.04
     dairy
    1.02
     train
    0.96
     farm
    0.94
     grain
    0.93
     unparalleled
    0.93
    ництво
    0.93
    Activations Density 0.029%

    No Known Activations