© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70684
    Prev
    Next
    INDEX
    Explanations

    Bengal, Bengali, Bengaluru

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

    The neuron activates on occurrences of the word stem “Bengal” (e.g. “Bengali,” “Bengal,” “Bengaluru,” 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
    </strong>
    -2.47
    
    -2.42
     puntas
    -2.38
     opposing
    -2.36
     necesarias
    -2.36
     agujas
    -2.33
     burbujas
    -2.33
    
    -2.28
     cejas
    -2.23
     ilustraciones
    -2.17
    POSITIVE LOGITS
    s
    2.44
    茈
    2.11
    嫆
    2.06
     trabalha
    2.03
    鲧
    2.02
    幸好
    2.00
    ↵
    1.99
    而在
    1.98
    畢竟
    1.94
     με
    1.93
    Activations Density 0.003%

    No Known Activations