© 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. 98016
    Prev
    Next
    INDEX
    Explanations

    supply chain

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

    The main thing this neuron does is detect the term “supply” (especially in supply-chain or supply-related contexts).

    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
    よ
    -1.00
    たちが
    -0.91
    チア
    -0.88
     systematic
    -0.86
    囯
    -0.86
    شان
    -0.85
    Spending
    -0.84
     conservación
    -0.83
    쓰
    -0.83
    スーツ
    -0.82
    POSITIVE LOGITS
     chain
    1.48
    supply
    1.42
     Supply
    1.38
     of
    1.29
     SUPPLY
    1.27
    Supply
    1.19
     supplying
    1.13
     supply
    1.10
     chains
    1.08
     dorada
    1.06
    Activations Density 0.016%

    No Known Activations