© 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. 10-GEMMASCOPE-RES-131K
    4. 12227
    Prev
    Next
    INDEX
    Explanations

    names of countries

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

    The neuron is specialized to pick up numerical data values (especially decimal or integer statistics) appearing alongside proper nouns or geographic/place names.

    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
     *"
    -1.54
     internasional
    -1.54
     menjelaskan
    -1.52
     Gehir
    -1.46
     masjid
    -1.40
    
    -1.40
    
    -1.38
     نداره
    -1.38
    cuid
    -1.37
     mengaku
    -1.35
    POSITIVE LOGITS
     Bhutan
    2.05
    ıyordu
    1.89
    They
    1.62
    abilirsiniz
    1.52
    他们的
    1.43
    躾
    1.43
     localObject
    1.42
     amount
    1.41
    Their
    1.40
              
    1.39
    Activations Density 0.004%

    No Known Activations