© 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. 103912
    Prev
    Next
    INDEX
    Explanations

    herpesvirus

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

    mentions of different types of viruses, particularly herpesviruses.

    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
     They
    -3.11
     This
    -2.92
     Their
    -2.45
    特效
    -2.41
     if
    -2.36
    婚礼
    -2.33
     nowadays
    -2.30
    ⟞
    -2.27
     hideous
    -2.27
    嫗
    -2.25
    POSITIVE LOGITS
    ↵↵
    3.16
    }
    3.00
    {
    2.78
    ”
    2.50
    悄悄
    2.31
    cornerRadius
    2.28
    2
    2.27
    槤
    2.27
    และ
    2.23
    ’
    2.22
    Activations Density 0.003%

    No Known Activations