© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49100
    Prev
    Next
    INDEX
    Explanations

    names starting with Edgar

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

    This neuron detects occurrences of the proper name “Edgar.”

    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
    tilizer
    -0.82
    表彰
    -0.82
    rån
    -0.80
    🍆
    -0.78
    پی
    -0.78
     Unders
    -0.76
    riques
    -0.74
    laught
    -0.73
     infallib
    -0.73
    cję
    -0.73
    POSITIVE LOGITS
     Allan
    0.89
     bhp
    0.82
     Allen
    0.79
    \#\#
    0.77
     Meyer
    0.74
    =[];
    0.73
    Allan
    0.73
     pytania
    0.71
     chiave
    0.71
    容
    0.70
    Activations Density 0.016%

    No Known Activations