© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40339
    Prev
    Next
    INDEX
    Explanations

    conditional keywords and assignments

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

    The neuron fires on numeric literals (bare numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     felpa
    -1.05
     would
    -1.00
    tableFuture
    -0.98
     that
    -0.98
     nothing
    -0.97
     estampado
    -0.94
    phäre
    -0.94
    ֨
    -0.93
     adornos
    -0.89
    emore
    -0.89
    POSITIVE LOGITS
     személy
    0.89
    注册
    0.79
     információ
    0.75
     sırt
    0.75
     fără
    0.75
    According
    0.73
     getM
    0.73
     négy
    0.73
     oğ
    0.72
     sınır
    0.72
    Activations Density 0.004%

    No Known Activations