© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36090
    Prev
    Next
    INDEX
    Explanations

    online presence and web content

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

    The neuron detects mentions of the internet or web (e.g. “online,” “web,” “internet,” “WEB”).

    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
     作成
    -1.13
    Also
    -1.10
     vorkommen
    -1.09
     名称
    -1.08
     盒
    -1.05
     impover
    -1.04
     菜单
    -1.03
     構造
    -1.02
    clearpage
    -1.01
     vendetta
    -1.01
    POSITIVE LOGITS
     online
    1.70
     internet
    1.45
     Internet
    1.38
    📱
    1.26
     web
    1.24
    💻
    1.24
     digital
    1.21
    online
    1.20
    www
    1.18
     онлайн
    1.13
    Activations Density 0.056%

    No Known Activations