© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114066
    Prev
    Next
    INDEX
    Explanations

    Sudan, Chad, Sea

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

    The neuron activates on proper names of African places and regions (e.g. Sudan, South Sudan, the Sahel, Chad, Darfur, Ndjamena).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    勦
    -1.85
     unangemess
    -1.82
    
    -1.80
    描く
    -1.75
    盉
    -1.75
     ("
    -1.70
     imó
    -1.66
     pequenas
    -1.63
     erhi
    -1.62
     But
    -1.60
    POSITIVE LOGITS
     When
    1.63
     После
    1.63
     memperbaiki
    1.57
     strut
    1.55
     några
    1.53
     amables
    1.44
     Когда
    1.41
     сколько
    1.39
     cuando
    1.38
     quando
    1.38
    Activations Density 0.007%

    No Known Activations