© 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. 65541
    Prev
    Next
    INDEX
    Explanations

    Jerusalem

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

    The neuron activates on mentions of geographic place names—especially city names like “Jerusalem,” “Hebron,” “Nablus,” etc.

    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
    
    -1.98
    鸰
    -1.89
    垍
    -1.88
    
    -1.88
    ーー
    -1.88
    するので
    -1.85
    不
    -1.85
    ~~~
    -1.84
     خاط
    -1.83
    謦
    -1.80
    POSITIVE LOGITS
    鍆
    1.71
     He
    1.65
     inherently
    1.61
     ADVERTISEMENT
    1.61
     Examining
    1.59
    ))$_
    1.57
     uniquement
    1.52
     nowadays
    1.52
     Trendy
    1.48
    翾
    1.46
    Activations Density 0.009%

    No Known Activations