© 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. 117045
    Prev
    Next
    INDEX
    Explanations

    surrounding and neighboring areas

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

    The neuron specifically detects the word “surrounding” when it modifies nearby nouns (e.g. surrounding areas/counties/regions).

    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
     précédentes
    -1.15
    '])
    -1.05
     précédents
    -0.99
     frontend
    -0.97
    たまた
    -0.96
    
    -0.96
     backend
    -0.96
     フレア
    -0.94
    somebody
    -0.94
    ironically
    -0.94
    POSITIVE LOGITS
     areas
    1.48
     area
    1.34
     because
    1.20
     communities
    1.16
     counties
    1.12
     countries
    1.11
     businesses
    1.08
     regions
    1.05
     sister
    1.04
     properties
    1.03
    Activations Density 0.042%

    No Known Activations