© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    immune system and function

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

    immune response

    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
    丁寧
    0.42
    𝄞
    0.42
    宵
    0.41
    淙
    0.41
     тексти
    0.40
    摩
    0.40
    скопа
    0.39
     कीजिएगा
    0.39
     renderEncoder
    0.39
    悦
    0.38
    POSITIVE LOGITS
    免疫
    3.56
     immune
    3.53
     имму
    3.45
     immun
    3.44
     Immune
    3.38
     immunological
    3.36
     immunity
    3.25
     Immun
    3.25
    immune
    3.20
     imun
    3.19
    Activations Density 0.162%

    No Known Activations