© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32751
    Prev
    Next
    INDEX
    Explanations

    steps and fitness tracker data

    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_40_width_262k_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
    早い
    0.43
    譽
    0.41
    離
    0.40
    arbeitung
    0.39
    迅速
    0.38
    名单
    0.38
    infix
    0.38
    序
    0.38
     Griffith
    0.38
     ಕಾರ
    0.38
    POSITIVE LOGITS
     Fitbit
    1.07
     tracking
    1.03
     trackers
    0.97
     tracker
    0.94
    Tracking
    0.85
    tracker
    0.84
     tracked
    0.83
     Tracking
    0.83
     wearable
    0.83
    tracking
    0.82
    Activations Density 0.011%

    No Known Activations