© 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. 70474
    Prev
    Next
    INDEX
    Explanations

    lagged words and phrases

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

    The neuron fires on any token containing the letter sequence “lag.”

    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
    鰨
    -3.00
    
    -3.00
    簠
    -2.92
     dieß
    -2.83
    罽
    -2.70
     sprüche
    -2.69
    uage
    -2.66
     anhänger
    -2.59
    崟
    -2.58
    峮
    -2.52
    POSITIVE LOGITS
    at
    3.08
    e
    2.95
    b
    2.95
    M
    2.95
    er
    2.81
    lag
    2.80
    g
    2.73
    O
    2.70
    c
    2.63
    =
    2.63
    Activations Density 0.006%

    No Known Activations