© 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. 54216
    Prev
    Next
    INDEX
    Explanations

    online stores and brands

    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
     jornal
    -0.75
     płat
    -0.71
     interviewing
    -0.71
    omina
    -0.71
     Consult
    -0.71
    iastes
    -0.71
    akte
    -0.71
    商業
    -0.71
    四十
    -0.70
     tributo
    -0.70
    POSITIVE LOGITS
     online
    1.48
     store
    1.35
     discount
    1.27
     supply
    1.15
     outlet
    1.11
    supply
    1.11
    online
    1.09
     stores
    1.09
     warehouse
    1.07
    Supply
    1.07
    Activations Density 0.073%

    No Known Activations