© 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. 11916
    Prev
    Next
    INDEX
    Explanations

    oligo compounds

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

    scientific terms related to oligosaccharides and oligomers in biochemistry and molecular biology.

    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
     They
    -2.16
    </b>
    -1.97
    But
    -1.94
     negara
    -1.88
     PÅ
    -1.86
     we
    -1.85
    😫
    -1.84
    一旁
    -1.83
     But
    -1.80
     bahwa
    -1.79
    POSITIVE LOGITS
    </h3>
    2.63
    "
    2.50
    ations
    2.06
     proactively
    2.03
    愎
    2.02
    垍
    1.95
    ו
    1.95
     мое
    1.93
    ,"
    1.91
    珹
    1.90
    Activations Density 0.013%

    No Known Activations