© 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. 95578
    Prev
    Next
    INDEX
    Explanations

    '.com' or '.org' addresses

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

    This neuron detects pieces of web addresses—especially domain-name components and URL tokens.

    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
    JHEP
    -1.22
     зеленый
    -1.09
     белой
    -1.05
    贋
    -1.03
    occur
    -1.02
     botellas
    -1.02
     vyroben
    -1.00
     деца
    -1.00
     белая
    -1.00
    bukaan
    -0.99
    POSITIVE LOGITS
     website
    1.04
    ？！”
    1.02
    8
    1.00
     ""
    0.90
     $(\%)$
    0.90
     study
    0.90
    istic
    0.90
    נוּ
    0.87
    ！！！”
    0.87
     []
    0.86
    Activations Density 0.033%

    No Known Activations