© 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. 58520
    Prev
    Next
    INDEX
    Explanations

    HIV AIDS epidemic financing

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

    references to HIV/AIDS in medical or news contexts.

    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
    謦
    -2.80
    注意事
    -2.73
    菒
    -2.64
    艄
    -2.58
    pulseira
    -2.53
    蹚
    -2.47
    臯
    -2.47
     unſ
    -2.41
     墊
    -2.34
    薆
    -2.34
    POSITIVE LOGITS
    1
    2.38
     
    2.20
    咆
    2.13
     When
    2.09
    ↵↵
    2.08
     Placing
    2.02
     mewujudkan
    2.00
     During
    1.99
     restful
    1.99
     Providing
    1.98
    Activations Density 0.001%

    No Known Activations