© 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-262K
    7. 15481
    Prev
    Next
    INDEX
    Explanations

    congenital birth defects

    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_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
     revenge
    0.52
    上涨
    0.51
    漲
    0.50
     käyttää
    0.50
     অত্যাচার
    0.49
     ماشین
    0.47
     Passenger
    0.47
     Shred
    0.47
    🇴
    0.47
     Timurtaş
    0.46
    POSITIVE LOGITS
     congenital
    1.04
     congén
    0.88
    先天
    0.80
     defects
    0.78
    出生
    0.76
     infants
    0.75
     neonatal
    0.75
    发育
    0.75
     developmental
    0.72
     defect
    0.71
    Activations Density 0.058%

    No Known Activations