© 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. 36393
    Prev
    Next
    INDEX
    Explanations

    laboratory values and ranges

    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
    税务
    0.58
    运营
    0.56
     ഉപകരണ
    0.54
    举办
    0.50
    㗽
    0.50
     تطوير
    0.50
    Economic
    0.49
     сельскохозяй
    0.49
    禊
    0.49
     제작
    0.49
    POSITIVE LOGITS
     blood
    0.85
     abnormalities
    0.80
     values
    0.79
     abnormal
    0.79
     abnormally
    0.76
     creatinine
    0.74
     cholesterol
    0.72
     indicators
    0.70
     healthy
    0.70
     indicator
    0.70
    Activations Density 0.101%

    No Known Activations