© 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. 7431
    Prev
    Next
    INDEX
    Explanations

    Southeast Asia

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

    This neuron detects occurrences of the geographic phrase “Southeast …” followed by a place name.

    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
     
    -4.34
    ↵↵
    -2.84
     …
    -2.75
     The
    -2.70
      
    -2.64
    </i>
    -2.56
     it
    -2.53
     ….
    -2.42
    少ない
    -2.41
    -
    -2.41
    POSITIVE LOGITS
    彞
    3.31
    ྅
    3.08
     土産
    3.00
    愎
    3.00
     grego
    2.95
    ⃒
    2.92
    
    2.88
    𐌹
    2.88
    ୌ
    2.88
    síða
    2.86
    Activations Density 0.006%

    No Known Activations