© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44633
    Prev
    Next
    INDEX
    Explanations

    dexamethasone or dextran

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

    chemical and medical terms starting with "dex", particularly in scientific contexts like "dextran" and "dexamethasone".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of the character sequence “dextr” (as in dextran, dextrous, dextrin, cyclodextrin, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    欉
    -2.98
     goederen
    -2.94
     groots
    -2.88
    ꜆
    -2.86
    猡
    -2.72
    诹
    -2.66
    .”.
    -2.55
    镔
    -2.53
     sterren
    -2.48
     voedsel
    -2.48
    POSITIVE LOGITS
    A
    2.91
    </h2>
    2.77
     '
    2.50
    ">
    2.50
    ,
    2.30
    2
    2.23
    有
    2.13
    也
    2.13
     leur
    2.09
    ii
    2.06
    Activations Density 0.004%

    No Known Activations