© 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. 105079
    Prev
    Next
    INDEX
    Explanations

    center alignment

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

    This neuron activates on code tokens that specify centering or center alignment in UI layouts.

    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
     pivotal
    -1.50
    甞
    -1.38
     the
    -1.34
     cerrada
    -1.31
     Dinas
    -1.30
     largely
    -1.30
    lan
    -1.28
     dismal
    -1.28
    rollment
    -1.27
     ayudan
    -1.27
    POSITIVE LOGITS
     during
    1.41
     could
    1.37
    Iš
    1.35
    Día
    1.35
     would
    1.34
     supremely
    1.27
     perpetually
    1.25
     massively
    1.22
     يمكنك
    1.21
     rodzic
    1.21
    Activations Density 0.004%

    No Known Activations