© 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. 93797
    Prev
    Next
    INDEX
    Explanations

    HIV virus subtypes

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

    content related to HIV-1 and its subtypes, particularly when discussing viral genetics, structure, or research.

    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
    Amar
    -0.83
    Ħ
    -0.71
    ат
    -0.71
    Pir
    -0.69
    ições
    -0.69
     Hispanics
    -0.69
    Shard
    -0.68
    nebago
    -0.68
     Amar
    -0.67
    рак
    -0.67
    POSITIVE LOGITS
     HIV
    2.06
    HIV
    1.61
     AIDS
    1.32
     Env
    1.10
     Retro
    1.05
    AIDS
    1.02
     hiv
    1.01
    hiv
    0.99
    LTR
    0.98
     env
    0.94
    Activations Density 0.135%

    No Known Activations