© 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. 118797
    Prev
    Next
    INDEX
    Explanations

    study of

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

    the phrase "study of" in academic or educational contexts.

    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
    ),
    -1.80
    "
    -1.77
     fréquemment
    -1.72
     Their
    -1.67
     partiellement
    -1.67
    >
    -1.62
     ка
    -1.62
     "
    -1.61
     How
    -1.57
     fortement
    -1.54
    POSITIVE LOGITS
     intently
    1.91
     how
    1.89
     why
    1.73
     oppervlak
    1.71
     être
    1.67
     снимки
    1.55
     and
    1.55
    蹌
    1.52
     intensively
    1.52
    ják
    1.50
    Activations Density 0.084%

    No Known Activations