© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3413
    Prev
    Next
    INDEX
    Explanations

    watch faces complications

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

    The neuron fires on tokens referring to Apple Watch–related APIs, classes, or feature/version numbers (e.g. “WatchKit,” “InterfaceController,” “watch,” “OS 4,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    熔
    -0.76
    ריכה
    -0.74
     EAST
    -0.74
     kü
    -0.71
    kamer
    -0.69
     Kiy
    -0.69
    Salta
    -0.68
     Miet
    -0.68
     berani
    -0.67
    ですので
    -0.66
    POSITIVE LOGITS
     Wear
    1.05
    Wear
    0.93
     Complications
    0.91
     alligator
    0.90
     watch
    0.90
    watch
    0.90
     wearable
    0.88
     Watch
    0.88
    Watch
    0.87
     complications
    0.85
    Activations Density 0.010%

    No Known Activations