© 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. 102972
    Prev
    Next
    INDEX
    Explanations

    adsorption and removal processes

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

    This neuron detects scientific terminology related to chemical sorption and adsorption processes, particularly in the context of materials science and environmental chemistry.

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

    The neuron fires strongly on scientific terms containing the substring “-orption” (as in adsorption, desorption, biosorption, sorption).

    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
     /><
    -0.88
    licing
    -0.85
    щаются
    -0.83
    faqs
    -0.79
    tiennent
    -0.77
     deterrence
    -0.75
     killers
    -0.75
     katkı
    -0.75
     mergers
    -0.71
    外交
    -0.71
    POSITIVE LOGITS
     equilibrium
    1.35
     adsorption
    1.30
     adsor
    1.20
     Freund
    1.20
     sor
    1.11
     Removal
    1.09
     batch
    1.09
     Adsorption
    1.08
     Equilibrium
    1.05
    Freund
    1.03
    Activations Density 0.044%

    No Known Activations