© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12761
    Prev
    Next
    INDEX
    Explanations

    busy, focused, or preoccupied

    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_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
     காணலாம்
    0.43
    Wen
    0.42
    Raises
    0.41
     taea
    0.39
    你可以
    0.38
     können
    0.38
    Happ
    0.38
    珢
    0.38
    สามารถ
    0.38
     использования
    0.38
    POSITIVE LOGITS
     distract
    0.96
     preoccupied
    0.96
     busy
    0.93
    忙
    0.92
     distracted
    0.89
     preoccupation
    0.89
     distraction
    0.86
     distractions
    0.86
     distracting
    0.83
    busy
    0.80
    Activations Density 0.089%

    No Known Activations