© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6019
    Prev
    Next
    INDEX
    Explanations

    medical conditions and care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Select
    0.55
    表
    0.48
     designing
    0.47
    Select
    0.46
    Dropdown
    0.44
    客
    0.44
     dropdown
    0.43
     G
    0.43
     JavaScript
    0.43
     دلچ
    0.42
    POSITIVE LOGITS
     illness
    0.95
    病情
    0.94
     hospitalization
    0.91
     Krankheit
    0.89
     medical
    0.89
     malattia
    0.89
     hospitalized
    0.88
     médicos
    0.88
     بیماری
    0.88
     leukemia
    0.87
    Activations Density 0.121%

    No Known Activations