© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8124
    Prev
    Next
    INDEX
    Explanations

    Chapel followed by location or type

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

    The main thing this neuron does is detect occurrences of the word “Chapel.”

    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
    真好
    -2.83
    {
    -2.77
     was
    -2.75
    瑨
    -2.73
    餿
    -2.72
    泔
    -2.70
    罽
    -2.67
    甃
    -2.47
    綃
    -2.45
    缡
    -2.44
    POSITIVE LOGITS
    r
    3.19
    All
    3.11
    On
    3.05
    For
    3.02
    d
    3.00
    4
    2.92
    7
    2.89
    al
    2.86
    As
    2.81
    ia
    2.80
    Activations Density 0.001%

    No Known Activations