© 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. 11774
    Prev
    Next
    INDEX
    Explanations

    urls and citations

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

    This neuron detects pieces of web URLs—domain names, path segments, and related tokens in links.

    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
    훤
    -0.82
     republiky
    -0.79
     Paola
    -0.78
     रही
    -0.76
     município
    -0.76
     involuntary
    -0.76
     Formato
    -0.75
    ₲
    -0.75
     normale
    -0.75
    tehen
    -0.75
    POSITIVE LOGITS
     Chief
    0.83
     Senior
    0.79
     including
    0.79
     brilliantly
    0.78
    ysk
    0.77
     bast
    0.76
     czer
    0.76
    しくない
    0.73
    トリック
    0.73
     bluff
    0.71
    Activations Density 0.165%

    No Known Activations