© 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. 10-GEMMASCOPE-RES-131K
    7. 44943
    Prev
    Next
    INDEX
    Explanations

    new tab or window

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

    This neuron detects phrases indicating that a link or resource will open in a new window or tab (e.g. “opens in a new window,” “opens in a new tab,” or external link indicators).

    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
    -
    -2.17
    and
    -2.09
     just
    -1.84
     numerous
    -1.80
     several
    -1.79
     adequate
    -1.77
     giving
    -1.74
     =
    -1.73
    te
    -1.73
     only
    -1.67
    POSITIVE LOGITS
     DIFFERENT
    1.94
    <0xE3>
    1.90
    짭
    1.84
    tagHelper
    1.82
     Geografía
    1.80
    鸲
    1.77
    cím
    1.75
     اولین
    1.75
    abilia
    1.72
    ordinaire
    1.71
    Activations Density 0.004%

    No Known Activations