© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    medical treatments and diseases

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

    phrases describing medications or treatments for medical conditions.

    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
    実装
    -0.86
    ime
    -0.81
     グラビア
    -0.78
     pilates
    -0.77
    Troy
    -0.77
    ഊ
    -0.77
    '].'
    -0.75
     野菜
    -0.73
    र्त
    -0.72
    gered
    -0.72
    POSITIVE LOGITS
     treatment
    3.41
     treat
    2.92
     treating
    2.72
    treatment
    2.36
    treat
    2.33
     Treatment
    2.31
     treats
    2.22
     Treat
    2.16
    Treatment
    2.14
    治疗
    2.13
    Activations Density 0.344%

    No Known Activations