© 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. 48090
    Prev
    Next
    INDEX
    Explanations

    wrapping or wrapped around something

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

    The neuron fires on occurrences of the root “wrap” (in any inflection such as wrap, wraps, wrapped, wrapping).

    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
    )
    -2.34
    '
    -2.03
     dopo
    -1.87
     REALLY
    -1.80
    vailable
    -1.78
    
    -1.77
    鶫
    -1.72
     %).
    -1.70
    
    -1.68
     durante
    -1.66
    POSITIVE LOGITS
     Wrap
    2.16
     phenomenal
    2.11
     innovative
    1.78
     continual
    1.76
     multifaceted
    1.72
     unrelenting
    1.72
     seductive
    1.71
     tricky
    1.71
     quaint
    1.70
     wrapping
    1.70
    Activations Density 0.021%

    No Known Activations