© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86032
    Prev
    Next
    INDEX
    Explanations

    carbon fiber and nanotubes

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

    materials made of carbon fibers or carbon nanotubes.

    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
    ’
    -2.34
     it
    -2.22
     these
    -1.97
     Then
    -1.81
     very
    -1.81
    人也
    -1.77
    但也
    -1.71
     way
    -1.70
    꾼
    -1.69
    myList
    -1.62
    POSITIVE LOGITS
    緜
    2.27
    および
    2.03
    别说
    1.87
     唯美
    1.84
    __":
    1.81
    makeConstraints
    1.80
    ፔ
    1.79
    
    1.78
    ValueGeneration
    1.77
    泐
    1.77
    Activations Density 0.003%

    No Known Activations