© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71738
    Prev
    Next
    INDEX
    Explanations

    lectin, agglutinin, in, affinity

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

    This neuron identifies scientific terms related to lectins and agglutination in biochemistry and molecular biology research.

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

    The neuron fires on biochemical protein names ending in “-in” (especially lectins and agglutinins).

    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
    葙
    -1.76
    说实话
    -1.75
    ſent
    -1.74
     terremoto
    -1.73
    Deux
    -1.73
    욘
    -1.73
    jelasan
    -1.73
     randon
    -1.72
    Ajouter
    -1.69
     cylind
    -1.68
    POSITIVE LOGITS
    le
    2.30
     is
    2.14
     to
    2.14
     he
    2.13
     on
    2.11
    end
    2.08
    N
    1.93
    <i>
    1.91
    >
    1.89
    d
    1.88
    Activations Density 0.033%

    No Known Activations