© 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. 34-GEMMASCOPE-RES-131K
    4. 76082
    Prev
    Next
    INDEX
    Explanations

    science and scientific inquiry

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

    text related to scientific research and academic discourse.

    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_34/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
     capitaine
    -0.80
     nesta
    -0.77
    otel
    -0.77
    Laptop
    -0.77
     Verd
    -0.77
    Shit
    -0.75
    oform
    -0.75
     poète
    -0.75
    Frontend
    -0.73
     okul
    -0.73
    POSITIVE LOGITS
     scientific
    6.47
     science
    6.19
    scientific
    4.91
    science
    4.59
     Science
    4.59
     scientists
    4.28
     Scientific
    4.28
    Scientific
    4.22
    科学
    4.16
     scientifically
    4.16
    Activations Density 0.141%

    No Known Activations