© 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. 10-GEMMASCOPE-RES-131K
    7. 60979
    Prev
    Next
    INDEX
    Explanations

    NI, Beatrice, Joanna, Nicola

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

    This neuron detects the appearance of a person’s proper name in the heading of a legal or court‐case document.

    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
     Would
    -2.69
     in
    -2.69
     HUGE
    -2.66
     With
    -2.61
     However
    -2.59
    I
    -2.59
    o
    -2.58
     Not
    -2.56
     {
    -2.56
     from
    -2.44
    POSITIVE LOGITS
    卝
    3.61
    橚
    3.50
    驁
    3.16
    栊
    3.06
    謦
    3.03
    糁
    3.02
    鐿
    2.98
     GRATIS
    2.94
     rusa
    2.94
    읗
    2.92
    Activations Density 0.005%

    No Known Activations