© 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. 10-GEMMASCOPE-RES-131K
    7. 8306
    Prev
    Next
    INDEX
    Explanations

    anti-inflammatory and antiviral activity

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

    mentions of chemical compounds or substances that have therapeutic or pharmacological properties.

    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
    ighed
    -1.73
    ЛЮ
    -1.48
    🔓
    -1.39
    igth
    -1.36
    ׳
    -1.35
     sachsen
    -1.35
    
    -1.35
    €™
    -1.34
     POLLUTION
    -1.32
     IMPLEMENT
    -1.30
    POSITIVE LOGITS
    1.63
    }
    1.58
    </h2>
    1.56
    ↵↵↵
    1.50
    ↵↵↵↵
    1.41
    ↵
    1.41
     both
    1.40
    ↵↵
    1.40
     overall
    1.34
     sorgfäl
    1.30
    Activations Density 0.334%
    No Known Activations