© 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. 10-GEMMASCOPE-RES-131K
    7. 101412
    Prev
    Next
    INDEX
    Explanations

    renamed, Created, Associated, WASHINGTON, Xsan

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

    The neuron fires on past-tense verb forms ending in “-ed.”

    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
    hending
    -1.80
     enfance
    -1.79
     eléctricas
    -1.78
    thschild
    -1.73
     maceta
    -1.73
     capucha
    -1.68
     hábiles
    -1.65
     CallOverrides
    -1.63
    🔸
    -1.60
     笑
    -1.59
    POSITIVE LOGITS
     is
    2.19
    in
    1.75
    re
    1.67
    up
    1.63
     اين
    1.63
    b
    1.60
    Élet
    1.57
    st
    1.55
     tiveram
    1.55
    Producción
    1.55
    Activations Density 0.000%

    No Known Activations