© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112087
    Prev
    Next
    INDEX
    Explanations

    email addresses and domains

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

    email addresses, specifically detecting the ".com" domain suffix.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects domain name tokens (like “com” or “org”) in URLs and email addresses.

    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
     anche
    -1.88
    籥
    -1.87
    trá
    -1.73
    \}$,
    -1.72
     également
    -1.67
    𐑂
    -1.63
    ]$,
    -1.62
     tudi
    -1.59
    \}$.
    -1.59
    \},
    -1.58
    POSITIVE LOGITS
    “
    1.41
    .
    1.37
        
    1.35
    Carex
    1.34
    其余
    1.29
     precioso
    1.28
     мають
    1.27
     other
    1.27
     czarny
    1.23
     ему
    1.22
    Activations Density 0.022%

    No Known Activations