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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8124
    Prev
    Next
    INDEX
    Explanations

    busy or occupied with activity

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

    lost or absorbed in thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idence
    0.37
     osk
    0.37
    OfDeath
    0.36
     amplitud
    0.36
    ോദ
    0.35
    +#
    0.35
    ക്കേണ്ട
    0.35
    स्फोट
    0.34
    鹼
    0.34
    鏄
    0.34
    POSITIVE LOGITS
     مشغول
    1.94
     preoccupied
    1.93
     busy
    1.84
     absorbed
    1.81
     occupied
    1.80
     engross
    1.80
     immersed
    1.77
    busy
    1.69
    忙
    1.66
    occupied
    1.59
    Activations Density 0.085%

    No Known Activations