© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4009
    Prev
    Next
    INDEX
    Explanations

    medical state or condition

    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_40_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
     रणनी
    0.45
     Oops
    0.45
    业绩
    0.44
     చేప
    0.43
     στι
    0.42
     SaaS
    0.41
     अवसरों
    0.41
    練
    0.41
     通勤
    0.41
     Flexibility
    0.40
    POSITIVE LOGITS
     hospital
    1.21
     hospitalization
    1.10
     अस्पताल
    1.07
     medics
    1.07
     paramedics
    1.06
     delirium
    1.02
     hospitalized
    1.02
     doctors
    1.01
    hospital
    1.00
     delir
    1.00
    Activations Density 0.165%

    No Known Activations