© 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. 41-GEMMASCOPE-2-RES-262K
    7. 24900
    Prev
    Next
    INDEX
    Explanations

    Medicare and healthcare terms

    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_all/layer_41_width_262k_l0_big
    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
    
    0.43
     useRouter
    0.42
     soát
    0.41
    uggish
    0.41
     भाव
    0.40
    Margin
    0.40
     libra
    0.39
    
    0.38
    elevationMap
    0.38
    istin
    0.38
    POSITIVE LOGITS
     Medicare
    0.63
    Medicare
    0.58
     False
    0.54
     Stark
    0.52
     medicare
    0.49
     false
    0.48
     Kick
    0.48
    False
    0.44
     undo
    0.44
    oflu
    0.44
    Activations Density 0.002%

    No Known Activations