© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83920
    Prev
    Next
    INDEX
    Explanations

    HIV, AIDS, infection, and treatment

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

    medical and scientific text about HIV/AIDS and related infections.

    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
    osidad
    -0.79
     cancelar
    -0.75
    Xiaomi
    -0.74
     validar
    -0.72
    xPos
    -0.71
    nige
    -0.70
    mTitle
    -0.70
    registry
    -0.70
     pegawai
    -0.70
    ónima
    -0.70
    POSITIVE LOGITS
     HIV
    1.98
    HIV
    1.79
    AIDS
    1.45
     AIDS
    1.36
     CD
    1.31
     ART
    1.03
     hiv
    0.99
     recons
    0.98
     marav
    0.97
     rebound
    0.96
    Activations Density 0.136%

    No Known Activations