© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87050
    Prev
    Next
    INDEX
    Explanations

    Kaiser Permanente, Kaiserslautern

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

    The neuron detects named entities, especially proper names of places and organizations (e.g. “Northern California” or “Kaiser Permanente”).

    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
     Č
    -0.85
     Nel
    -0.81
    Č
    -0.80
     הי
    -0.79
     woj
    -0.76
     edits
    -0.76
     kons
    -0.73
     JEE
    -0.72
    修复
    -0.71
    CHAP
    -0.71
    POSITIVE LOGITS
     Permanente
    1.11
     HMO
    0.90
     permanente
    0.89
     Kaiser
    0.88
    Perman
    0.81
     kaiser
    0.81
    rometry
    0.74
    craft
    0.73
     Rass
    0.73
     kwamen
    0.73
    Activations Density 0.031%

    No Known Activations