© 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. 34-GEMMASCOPE-RES-131K
    7. 93256
    Prev
    Next
    INDEX
    Explanations

    pectin and enzymes

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

    scientific terms related to plant polysaccharides and cell wall components, particularly pectins, arabinans, and galacturonase.

    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_34/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
     Kig
    -0.82
    êques
    -0.79
    XmlEnum
    -0.79
    žd
    -0.78
    🗣
    -0.77
     Tidal
    -0.75
    ❄️
    -0.74
    čar
    -0.74
    ᄂ
    -0.73
    pren
    -0.72
    POSITIVE LOGITS
     pectin
    1.21
     fruit
    0.86
     deme
    0.86
     apple
    0.81
     HG
    0.80
    pect
    0.80
     homog
    0.79
     pect
    0.78
     pec
    0.74
     LM
    0.74
    Activations Density 0.091%

    No Known Activations