© 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. 112798
    Prev
    Next
    INDEX
    Explanations

    world reports and news

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

    The neuron strongly responds to mentions of the publication title “U.S. News & World Report.”

    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
     and
    -2.31
    {
    -1.60
    <bos>
    -1.51
    擁有
    -1.50
     enables
    -1.47
     intricacies
    -1.46
     enhances
    -1.46
     hvilken
    -1.45
    (*´
    -1.43
     måned
    -1.41
    POSITIVE LOGITS
     a
    2.72
     VERY
    1.98
     Lesen
    1.88
    事も
    1.84
     of
    1.74
     Now
    1.74
     largely
    1.73
     also
    1.73
     somewhat
    1.72
     REALLY
    1.66
    Activations Density 0.022%

    No Known Activations