© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3089
    Prev
    Next
    INDEX
    Explanations

    screening for 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-it/resid_post/layer_16_width_262k_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
    t
    0.81
    sel
    0.75
    ห
    0.71
    sen
    0.70
    sl
    0.68
    อง
    0.68
    .
    0.68
    k
    0.67
    를
    0.66
     world
    0.66
    POSITIVE LOGITS
     screening
    1.17
     Screening
    1.09
     screenings
    1.07
     screened
    0.95
     स्क्रीनिंग
    0.92
    screening
    0.89
     riesgos
    0.80
    ၅
    0.80
     obstáculos
    0.77
    ᱖
    0.77
    Activations Density 0.003%

    No Known Activations