© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39005
    Prev
    Next
    INDEX
    Explanations

    waterfront, beachfront, seaside locations

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

    The neuron activates on mentions of “waterfront” or related terms indicating proximity to water (e.g., waterfront living, marina waterfront).

    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
    {
    -2.09
    人們
    -1.90
    因为
    -1.88
    蛩
    -1.88
     Hinblick
    -1.86
    ￪
    -1.80
    由
    -1.77
    In
    -1.77
    同樣
    -1.70
    鉭
    -1.70
    POSITIVE LOGITS
    ஂ
    2.27
     of
    2.05
    着手
    1.96
    abinieri
    1.95
    沨
    1.95
     earliest
    1.94
    喏
    1.91
     They
    1.82
    麋
    1.81
    /"
    1.80
    Activations Density 0.009%

    No Known Activations