© 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. 10-GEMMASCOPE-RES-131K
    7. 10115
    Prev
    Next
    INDEX
    Explanations

    HIV-1 following terms

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

    mentions of HIV-1 and associated terminology in medical or scientific 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
    At
    -2.27
    .”
    -2.13
    l
    -1.95
    7
    -1.88
     )
    -1.88
    ).
    -1.86
    '
    -1.84
    ↵
    -1.84
    x
    -1.82
    );
    -1.80
    POSITIVE LOGITS
    龶
    2.30
    鸸
    2.23
    栊
    2.22
    ErrUnexpectedEOF
    2.17
    鹩
    2.16
    蟊
    2.13
    鲧
    2.09
     seleccionadas
    2.08
    ༔
    2.06
    醅
    2.05
    Activations Density 0.044%

    No Known Activations