© 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. 104222
    Prev
    Next
    INDEX
    Explanations

    laboratory equipment and substances

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

    laboratory and scientific procedures involving liquids, solutions, and scientific apparatus like pipettes.

    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
     geene
    -1.72
     ۱۱
    -1.70
    ActionCreators
    -1.47
     kredi
    -1.45
     melk
    -1.45
     panik
    -1.44
     otel
    -1.43
     kuv
    -1.42
    icie
    -1.41
     ۱۷
    -1.41
    POSITIVE LOGITS
     were
    1.75
     Despite
    1.72
     during
    1.71
     Although
    1.59
     Providing
    1.52
     after
    1.48
     Having
    1.48
     required
    1.47
     within
    1.46
     had
    1.41
    Activations Density 0.137%

    No Known Activations