© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    societal structures

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

    of the human experience

    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
     ![
    0.42
     Some
    0.40
     نکات
    0.40
     einzelne
    0.40
     প্রচুর
    0.40
     Different
    0.38
     ONLY
    0.38
     Such
    0.38
    ([
    0.37
     Various
    0.37
    POSITIVE LOGITS
     society
    1.45
    society
    1.18
     Christendom
    1.06
     humanity
    1.05
     academia
    1.05
     mankind
    1.05
     humankind
    1.02
     capitalism
    1.02
     modern
    1.01
     civilization
    1.01
    Activations Density 0.631%

    No Known Activations