© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    nursing instructions and patient 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/transcoder_all/layer_40_width_262k_l0_small_affine
    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
     orde
    0.41
     प्रेम
    0.39
     denial
    0.37
    TDto
    0.37
     reducción
    0.37
    まして
    0.36
    乆
    0.36
     long
    0.35
     групп
    0.35
    宵
    0.35
    POSITIVE LOGITS
     nursing
    0.98
    Nursing
    0.97
     Nursing
    0.92
     नर्सिंग
    0.72
    看護
    0.72
     nurse
    0.70
     nurs
    0.69
    Nurse
    0.67
    护理
    0.66
     nurses
    0.65
    Activations Density 0.036%

    No Known Activations