© 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. 80753
    Prev
    Next
    INDEX
    Explanations

    centre for

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

    The neuron detects occurrences of the word “centre” or “center” (in various capitalizations) as part of institutional or 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
     участия
    -1.95
    
    -1.92
     obstáculos
    -1.87
    owm
    -1.57
     большого
    -1.56
     Wohnzimmer
    -1.56
     bedrag
    -1.55
     quinze
    -1.52
     параметров
    -1.52
     большо
    -1.52
    POSITIVE LOGITS
     decis
    1.68
    k
    1.67
    center
    1.65
    ⽼
    1.62
    焢
    1.60
    most
    1.59
     will
    1.59
     medicina
    1.59
     figlia
    1.57
    m
    1.57
    Activations Density 0.028%

    No Known Activations