© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116475
    Prev
    Next
    INDEX
    Explanations

    HIV/AIDS prevention and care

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

    content related to HIV/AIDS and public health information.

    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
     ج
    -0.84
    Ако
    -0.82
     pasas
    -0.79
     extrusion
    -0.77
     selfie
    -0.73
    pley
    -0.71
    Какие
    -0.71
     cuerpo
    -0.70
     Werte
    -0.69
     mengel
    -0.69
    POSITIVE LOGITS
     HIV
    1.13
    HIV
    1.09
     workplace
    1.02
     AIDS
    1.00
     responses
    1.00
     response
    0.92
    AIDS
    0.87
    prevention
    0.85
     prevention
    0.84
    Prevention
    0.81
    Activations Density 0.045%

    No Known Activations