© 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. 23961
    Prev
    Next
    INDEX
    Explanations

    glory lane

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

    This neuron activates specifically on the word “glory.”

    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
    逦
    -2.91
     玩具
    -2.72
    ꦸ
    -2.52
     妹
    -2.50
    Revenir
    -2.50
    缈
    -2.48
    ⽤
    -2.45
    MessageTagHelper
    -2.42
    妧
    -2.41
    鋇
    -2.39
    POSITIVE LOGITS
    2
    2.64
    _
    2.42
    7
    2.41
    ጵ
    2.38
    3
    2.27
    ]
    2.27
    1
    2.19
     retrô
    2.19
     In
    2.17
     
    2.17
    Activations Density 0.001%

    No Known Activations