© 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. 81168
    Prev
    Next
    INDEX
    Explanations

    healthcare professions

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

    deregulation, tax cuts and growth

    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
    ni
    0.46
     komment
    0.45
    罍
    0.43
    to
    0.43
    Nos
    0.43
    été
    0.42
    Able
    0.42
    㖷
    0.42
    বাঙ্গ
    0.42
    传统的
    0.42
    POSITIVE LOGITS
     healthcare
    0.52
     dressings
    0.49
    healthcare
    0.49
     clothed
    0.48
    oL
    0.48
    ↵
    0.47
    HEALTH
    0.45
    حيان
    0.45
    concurrent
    0.44
     health
    0.43
    Activations Density 0.001%

    No Known Activations