© 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. 58611
    Prev
    Next
    INDEX
    Explanations

    ligand binding

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

    references to ligands and receptor binding in scientific/biochemical contexts.

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

    The neuron specializes in detecting the term “ligand” (including its hyphenated and morphological variants) in biochemical text.

    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
    </strong>
    -2.28
    綃
    -2.27
    ”
    -2.23
    that
    -2.16
    焢
    -2.13
     美甲
    -2.11
    or
    -2.11
    ):
    -2.09
    注意事
    -2.06
    ઁ
    -2.05
    POSITIVE LOGITS
    \
    2.69
     AND
    2.33
     THEIR
    2.30
     和
    2.23
     должна
    2.20
     esperar
    2.19
    up
    2.19
    们的
    2.11
    崛起
    2.09
     eléctrico
    2.06
    Activations Density 0.019%

    No Known Activations