© 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. 4692
    Prev
    Next
    INDEX
    Explanations

    body parts and health conditions

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

    body parts and health conditions

    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
    ตัว
    0.49
     दिलों
    0.48
     सिलसिला
    0.48
     પગ
    0.47
    মহান
    0.46
     इनकम
    0.46
    耦
    0.44
    体内
    0.41
    کنندگان
    0.40
     выру
    0.39
    POSITIVE LOGITS
     disorders
    0.85
     region
    0.80
     tissues
    0.77
     anatomy
    0.77
    炎
    0.76
     parenchyma
    0.75
     mucosa
    0.73
     epithelium
    0.71
     injuries
    0.70
     muscles
    0.70
    Activations Density 0.197%

    No Known Activations