© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3119
    Prev
    Next
    INDEX
    Explanations

    news article URLs

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

    This neuron detects parts of web addresses (URLs), such as domain names, “http://”, slashes, and “.com.”

    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
     churn
    -0.75
    MouseClicked
    -0.75
     poema
    -0.72
     Clinic
    -0.72
    fileupload
    -0.71
     getting
    -0.71
    تری
    -0.69
     kuwa
    -0.69
    yung
    -0.68
    ギ
    -0.68
    POSITIVE LOGITS
    article
    1.04
     MSN
    1.02
    oped
    1.02
     articles
    1.02
     archives
    0.99
    hosted
    0.96
     artículo
    0.95
    articles
    0.94
     ARTICLE
    0.93
     article
    0.90
    Activations Density 0.037%

    No Known Activations