© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114083
    Prev
    Next
    INDEX
    Explanations

    responsibilities, interventions, assessment

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

    medical, economic, and technical terms

    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
    Negative Logits
    👘
    0.56
     일본
    0.52
    衣装
    0.50
    岐阜
    0.49
     whatnot
    0.48
    buatan
    0.47
     पोशा
    0.46
    噂
    0.46
    日本
    0.46
    👑
    0.46
    POSITIVE LOGITS
     triage
    0.59
     inpatient
    0.55
     acutely
    0.55
     interventions
    0.54
     assessment
    0.54
     caseload
    0.53
     varies
    0.51
     Medicaid
    0.50
     homelessness
    0.50
     intervention
    0.49
    Activations Density 0.000%

    No Known Activations