© 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. 104192
    Prev
    Next
    INDEX
    Explanations

    Russ and Essex

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

    The neuron strongly activates on occurrences of the toponym “Essex.”

    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
    '
    -3.45
    ↵
    -2.67
    </h3>
    -2.47
    你了
    -2.25
     放題
    -2.08
     gewähr
    -1.99
     Однако
    -1.95
    읖
    -1.95
    र्स
    -1.94
     통해
    -1.93
    POSITIVE LOGITS
     некоторы
    2.59
    挲
    2.58
    蛲
    2.36
     και
    2.34
     ſie
    2.30
    ⚋
    2.30
    佧
    2.28
    is
    2.25
     一个
    2.17
     you
    2.16
    Activations Density 0.002%

    No Known Activations