© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51635
    Prev
    Next
    INDEX
    Explanations

    smartwatches and fitness trackers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    簽證
    0.48
    AIRE
    0.48
     арен
    0.46
    道具
    0.45
    +#+#
    0.45
    諺
    0.45
    
    0.45
    𝔱
    0.44
    機場
    0.44
     textarea
    0.44
    POSITIVE LOGITS
     wearable
    0.91
     wearables
    0.91
     smartwatch
    0.90
     wrist
    0.86
     Fitbit
    0.83
     Wrist
    0.76
     Wear
    0.73
     Bluetooth
    0.70
     wrists
    0.69
     Health
    0.69
    Activations Density 0.046%

    No Known Activations