© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33078
    Prev
    Next
    INDEX
    Explanations

    novel compounds and derivatives

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

    scientific or patent text describing chemical compounds or formulations.

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

    This neuron detects patent-style boilerplate phrasing that introduces the invention, especially “the present invention relates to novel … derivatives” and similar scope-setting language.

    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
     kepolisian
    -0.84
    conse
    -0.82
     listView
    -0.79
     Ortsteil
    -0.78
     Lido
    -0.78
    RelativePath
    -0.76
     déplo
    -0.76
    Kc
    -0.74
    Björn
    -0.74
    VSS
    -0.74
    POSITIVE LOGITS
     compounds
    1.66
     compound
    1.48
     Compound
    1.23
     Compounds
    1.13
     Formula
    1.09
    compound
    1.09
     process
    1.06
    process
    1.00
     formula
    0.99
    comp
    0.96
    Activations Density 0.110%

    No Known Activations