© 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. 22-GEMMASCOPE-RES-131K
    7. 13151
    Prev
    Next
    INDEX
    Explanations

    online shop

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

    The neuron flags occurrences of the word “shop,” especially in URLs or e-commerce contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    屃
    -2.66
     parachoque
    -2.31
    鸲
    -2.20
    轵
    -2.14
    泔
    -2.03
    舠
    -2.02
    咴
    -1.98
     paciencia
    -1.98
     comunión
    -1.95
     gebeurt
    -1.95
    POSITIVE LOGITS
    
    2.47
    ed
    2.42
    獗
    2.38
     renovations
    2.36
    }}
    2.19
    [
    2.17
    家に
    2.16
    ꜆
    2.16
     burbu
    2.14
     большим
    2.11
    Activations Density 0.011%

    No Known Activations