© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47246
    Prev
    Next
    INDEX
    Explanations

    health care contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    health care workers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ן
    0.80
    ルの
    0.79
    он
    0.79
    னர்
    0.78
    ък
    0.77
    скохозяй
    0.75
     específ
    0.73
     socketList
    0.72
    تين
    0.72
     cultivés
    0.72
    POSITIVE LOGITS
     in
    1.13
    ak
    1.09
    giver
    1.02
    f
    0.98
    ari
    0.97
    n
    0.96
    ag
    0.94
    ig
    0.89
    us
    0.88
    es
    0.86
    Activations Density 0.027%

    No Known Activations