© 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. 104650
    Prev
    Next
    INDEX
    Explanations

    experimental animal studies

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

    scientific text related to animal experiments in rats and mice, particularly focusing on medical and biological research.

    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
     Eſ
    -1.92
     ſon
    -1.74
     Inſ
    -1.73
     ſal
    -1.72
     ſp
    -1.64
    啐
    -1.60
     delightfully
    -1.59
     ſol
    -1.59
     vytvá
    -1.56
    撂
    -1.52
    POSITIVE LOGITS
     during
    2.16
     or
    2.11
     after
    1.84
     despite
    1.84
     heightened
    1.77
     three
    1.74
     by
    1.73
     without
    1.70
     several
    1.70
    engelsk
    1.69
    Activations Density 1.374%

    No Known Activations