© 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. 67654
    Prev
    Next
    INDEX
    Explanations

    Jed, Egy, Viena, Jeddah, Yeezy

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

    The neuron strongly activates on the letter sequence “jed” (e.g. the name “Jed” or any token containing “jed”).

    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
     traditionellen
    -2.61
    h
    -2.58
     '
    -2.52
     zentralen
    -2.50
     damaligen
    -2.44
    神情
    -2.44
    лерея
    -2.41
    臯
    -2.41
    这些
    -2.38
     splendid
    -2.38
    POSITIVE LOGITS
    苳
    2.42
    /).
    2.38
    eadilan
    2.27
    鯓
    2.25
    鏐
    2.23
    تاح
    2.19
    玧
    2.19
    guitar
    2.19
    😈
    2.17
    
    2.16
    Activations Density 0.002%

    No Known Activations