© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32751
    Prev
    Next
    INDEX
    Explanations

    sleep tracking, health, activity

    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_all/layer_41_width_262k_l0_big
    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
     searching
    0.47
     substitution
    0.46
    ERCIAL
    0.46
     search
    0.45
     parallelism
    0.43
     جست
    0.43
    騇
    0.42
    parallel
    0.41
    IMENT
    0.41
    COLLATION
    0.41
    POSITIVE LOGITS
     Fitbit
    0.89
     reminders
    0.81
     Bluetooth
    0.79
     personalised
    0.77
     앱
    0.77
    Coach
    0.76
     Coach
    0.75
    提醒
    0.74
    Diary
    0.73
     tracker
    0.73
    Activations Density 0.004%

    No Known Activations