© 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. 898
    Prev
    Next
    INDEX
    Explanations

    polymethyl methacrylate

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

    chemical polymers and their compounds, especially acrylates and methacrylates.

    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
     of
    -1.94
    er
    -1.91
    ve
    -1.87
     i
    -1.86
    ar
    -1.85
     has
    -1.68
    N
    -1.59
    其他
    -1.59
     riuscito
    -1.52
    ть
    -1.50
    POSITIVE LOGITS
     misalnya
    1.67
     Normalmente
    1.63
    听到了
    1.57
     motores
    1.57
    ギュア
    1.54
    四处
    1.49
    譙
    1.46
    旰
    1.45
     ARNOLD
    1.45
     ندارم
    1.43
    Activations Density 0.043%

    No Known Activations