© 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. 66197
    Prev
    Next
    INDEX
    Explanations

    lectin, concanavalin, phytohaemagglutinin, phorbol esters

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

    scientific terminology related to lectins and biochemical compounds used in laboratory research.

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

    The neuron fires on biochemical compound names ending in “-in,” such as lectins and related protein or glyco­protein names.

    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
    </td>
    -1.95
    ",
    -1.90
    ',
    -1.84
    </h2>
    -1.64
    ковым
    -1.55
    da
    -1.54
    ds
    -1.52
    u
    -1.49
    "
    -1.44
    Ll
    -1.43
    POSITIVE LOGITS
    豋
    1.57
    iriman
    1.50
    ﾈ
    1.41
    捽
    1.41
    gül
    1.40
    焄
    1.40
    蝸
    1.37
    Before
    1.37
    During
    1.36
    OBJET
    1.34
    Activations Density 0.055%

    No Known Activations