© 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. 21730
    Prev
    Next
    INDEX
    Explanations

    font-family or font names

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

    The neuron fires on standalone numeric literals (integers or floats) in code, especially CSS values.

    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
     it
    -2.05
     Then
    -1.77
     then
    -1.66
    甚至
    -1.45
     Its
    -1.43
     THEY
    -1.41
    fordshire
    -1.39
    。"
    -1.39
     Therefore
    -1.35
    年も
    -1.34
    POSITIVE LOGITS
     Otras
    1.45
    真实的
    1.35
     ipod
    1.30
     Otros
    1.30
    鎳
    1.28
     reichlich
    1.27
    那个人
    1.27
     conforman
    1.24
     AssemblyCompany
    1.23
     skrive
    1.23
    Activations Density 0.012%

    No Known Activations