© 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. 58970
    Prev
    Next
    INDEX
    Explanations

    urls starting with www

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

    The neuron is triggered by the “www” token in URLs, effectively spotting web‐address prefixes.

    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
     On
    -0.87
    árez
    -0.85
    𝓼
    -0.82
     which
    -0.81
    </td>
    -0.78
     when
    -0.77
    ????
    -0.75
     کرنے
    -0.73
     rowspan
    -0.72
     ignore
    -0.71
    POSITIVE LOGITS
    wwwwwwww
    1.27
    wwww
    1.17
    wwwww
    1.08
     delgado
    1.05
     enamorado
    1.04
    ↑↑↑
    1.01
    Jerome
    1.00
     vivent
    1.00
     éton
    1.00
     mourir
    1.00
    Activations Density 0.005%

    No Known Activations