© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1861
    Prev
    Next
    INDEX
    Explanations

    specialist healthcare teams or services

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

    healthcare and medical institutions or clinical settings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Podob
    -0.85
    counts
    -0.80
    構造
    -0.77
    련
    -0.77
     sztuk
    -0.76
    東大
    -0.75
     aggiorn
    -0.75
     ferner
    -0.74
     polskiego
    -0.73
    要用
    -0.73
    POSITIVE LOGITS
     teams
    1.16
     team
    1.09
    team
    0.91
     Team
    0.90
     Teams
    0.90
    XRD
    0.86
     services
    0.83
     mathvariant
    0.82
    teams
    0.81
     TEAM
    0.79
    Activations Density 0.048%

    No Known Activations