© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11573
    Prev
    Next
    INDEX
    Explanations

    polyurethane adhesives foam

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

    chemical terms and polymer compounds, especially those containing "polyurethane" and related chemical components.

    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
     mám
    -1.79
     in
    -1.77
    といって
    -1.70
    #(
    -1.65
     ........
    -1.61
     .......
    -1.60
    ются
    -1.59
    🧌
    -1.57
     chè
    -1.56
    ꪔ
    -1.54
    POSITIVE LOGITS
    </b>
    2.02
    }$.
    1.82
    ↵↵
    1.80
    猻
    1.74
     zuvor
    1.64
     be
    1.63
    ↵
    1.61
    s
    1.58
     damals
    1.56
     esclusivamente
    1.52
    Activations Density 0.061%

    No Known Activations