© 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. 34-GEMMASCOPE-RES-131K
    7. 93147
    Prev
    Next
    INDEX
    Explanations

    global economic trade conditions

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

    The neuron detects mentions of global-scale business or organizational roles and activities (e.g. “Global,” “worldwide,” leadership titles like “Head of”).

    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
    全国
    -2.00
     nationwide
    -1.92
     statewide
    -1.77
     Nationwide
    -1.59
     nationally
    -1.41
     Statewide
    -1.34
    国内
    -1.28
     nacional
    -1.27
     全国
    -1.16
    Nation
    -1.12
    POSITIVE LOGITS
    🌏
    1.43
    🌎
    1.34
    leader
    1.06
    🌍
    1.04
     Scam
    0.98
     fenô
    0.97
    izate
    0.94
     grans
    0.92
    leaders
    0.91
     standart
    0.91
    Activations Density 0.086%

    No Known Activations