© 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. 7323
    Prev
    Next
    INDEX
    Explanations

    Gulf of or Bay of

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

    The neuron detects mentions of named bodies of water—especially occurrences of “Gulf of …” geographic phrases.

    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
    岨
    -2.20
    塒
    -2.11
    Ꮴ
    -2.02
     promessa
    -2.02
     parachoque
    -1.95
    筇
    -1.94
     diing
    -1.93
    悭
    -1.92
     レスト
    -1.91
     cioc
    -1.91
    POSITIVE LOGITS
      
    2.80
     {
    2.27
     '
    2.13
    (
    2.13
     E
    2.03
    ↵
    2.02
     
    1.93
     L
    1.91
    ."
    1.89
     [
    1.88
    Activations Density 0.011%

    No Known Activations