© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    God's actions and attributes

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

    divine benevolent oversight

    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
     हंगामा
    0.44
     ಪಡೆಯ
    0.43
     получать
    0.43
    惴
    0.41
    捱
    0.41
    椒
    0.40
    ეკ
    0.38
     নিজেরাই
    0.38
    MOB
    0.38
     फंस
    0.38
    POSITIVE LOGITS
     merciful
    1.13
    赐
    0.98
     Himself
    0.98
     mercy
    0.96
     intervene
    0.95
     bestow
    0.93
     blessing
    0.90
     omn
    0.89
     intervened
    0.89
     miseric
    0.89
    Activations Density 0.180%

    No Known Activations