© 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. 90374
    Prev
    Next
    INDEX
    Explanations

    county names

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

    The neuron detects mentions of geographic place names (especially counties or regions).

    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
     Vra
    -0.88
     determina
    -0.88
     centrif
    -0.79
     tiss
    -0.78
     mín
    -0.78
    ⚓
    -0.77
     /#
    -0.77
     orizz
    -0.77
     dita
    -0.76
     Kend
    -0.75
    POSITIVE LOGITS
     County
    4.56
     county
    3.66
     COUNTY
    3.28
    County
    3.23
    county
    2.59
    COUNTY
    2.34
    县
    2.28
     counties
    1.95
    県
    1.80
    縣
    1.77
    Activations Density 0.067%

    No Known Activations