© 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. 103159
    Prev
    Next
    INDEX
    Explanations

    inventory and cost of goods

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     calcium
    -0.89
    Calcium
    -0.85
     arrears
    -0.84
     Calcium
    -0.84
    pregunt
    -0.75
     waschen
    -0.75
     BTC
    -0.73
    čním
    -0.72
     hacían
    -0.72
    лу
    -0.71
    POSITIVE LOGITS
     inventory
    1.38
     merchandise
    1.25
    inventory
    1.16
     goods
    1.15
     Cost
    1.06
     cost
    1.04
    Cost
    1.03
    cost
    1.01
    COST
    1.00
     ending
    0.98
    Activations Density 0.007%

    No Known Activations