© 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. 99857
    Prev
    Next
    INDEX
    Explanations

    surrounded by

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

    The neuron detects occurrences of the past-participle “surrounded,” especially in the phrase “surrounded by.”

    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
    S
    -2.75
     berdua
    -2.14
    L
    -2.02
    琑
    -2.02
     not
    -2.02
     If
    -2.02
    W
    -2.00
    </b>
    -1.97
     diverse
    -1.95
    ﮨ
    -1.94
    POSITIVE LOGITS
    苙
    2.48
     wn
    2.47
    ⏑
    2.42
     ſol
    2.41
    媗
    2.36
    罴
    2.31
     dreary
    2.30
    
    2.28
    </h3>
    2.27
     unending
    2.23
    Activations Density 0.012%

    No Known Activations