© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59754
    Prev
    Next
    INDEX
    Explanations

    polymerization

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

    chemical and material science terms specifically looking for the word "polymer" and related composite materials.

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

    The neuron strongly activates on the stem “polymer” (e.g. polymer, polymerization, polymerase, 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_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
     polymers
    -1.02
     polynomial
    -1.01
     polynomials
    -1.00
     polymer
    -0.95
     politics
    -0.85
    polynomial
    -0.81
     attribué
    -0.77
     political
    -0.75
     polycarbonate
    -0.75
     polygons
    -0.73
    POSITIVE LOGITS
    isation
    1.51
    izations
    1.37
    ization
    1.30
    izable
    1.19
    IZATION
    1.07
    isations
    1.05
    phism
    1.05
    ISATION
    1.04
    izador
    1.03
    ⛤
    1.02
    Activations Density 0.068%

    No Known Activations