© 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. 10-GEMMASCOPE-RES-131K
    7. 112707
    Prev
    Next
    INDEX
    Explanations

    health and medical services

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

    healthcare terminology and medical service descriptions.

    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_10/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
    繽
    -1.18
     dicono
    -1.06
    itudinal
    -1.05
    рене
    -1.05
    掘り
    -1.03
    自杀
    -1.03
    髄
    -0.97
    Kval
    -0.97
     falsi
    -0.97
     Piv
    -0.96
    POSITIVE LOGITS
     when
    1.35
     why
    1.31
     or
    1.30
    ándo
    1.27
     always
    1.27
    imbangan
    1.21
     those
    1.21
     udara
    1.20
     for
    1.18
    ǽ
    1.16
    Activations Density 0.104%

    No Known Activations