© 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. 34-GEMMASCOPE-RES-131K
    7. 76155
    Prev
    Next
    INDEX
    Explanations

    website .com domains

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

    The neuron detects web domain names or URLs (i.e. tokens comprising hostnames and “.com/.org” style fragments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     such
    -0.96
     такъ
    -0.89
    organisation
    -0.89
    ниците
    -0.84
    organization
    -0.80
    certain
    -0.77
     organização
    -0.77
    组织
    -0.75
     without
    -0.75
     constitucional
    -0.75
    POSITIVE LOGITS
    com
    1.60
     company
    1.45
    公司
    1.31
     com
    1.10
     companies
    1.04
     شرکت
    0.98
    COMPANY
    0.96
    COM
    0.96
    τικ
    0.93
    indd
    0.93
    Activations Density 0.034%

    No Known Activations