© 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. 34-GEMMASCOPE-RES-131K
    7. 7163
    Prev
    Next
    INDEX
    Explanations

    augmented reality virtual reality

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

    The neuron activates on mentions of augmented- or virtual-reality terms (e.g. “AR,” “augmented reality,” “VR,” “virtual”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    닷
    -0.84
     hablan
    -0.75
    此時
    -0.74
    了一下
    -0.73
    センサー
    -0.72
     empiezan
    -0.70
     الدولية
    -0.69
     interesse
    -0.69
     lançado
    -0.69
     び
    -0.68
    POSITIVE LOGITS
     reality
    1.32
     Reality
    1.19
     augmented
    1.12
    reality
    1.08
     augment
    1.04
     Augmented
    1.04
     environments
    1.00
    aug
    0.99
    mixed
    0.95
    Reality
    0.95
    Activations Density 0.019%

    No Known Activations