© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31644
    Prev
    Next
    INDEX
    Explanations

    shop around

    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
     rafters
    -0.82
    vrigt
    -0.81
     Ripple
    -0.79
    跏
    -0.76
     algal
    -0.76
    %>
    -0.75
     Stool
    -0.75
     "{{
    -0.75
    хва
    -0.74
     sikkert
    -0.74
    POSITIVE LOGITS
     shopping
    4.56
     shop
    3.66
    shopping
    3.61
     Shopping
    3.52
    Shopping
    3.42
    Shop
    3.00
     Shop
    2.92
    shop
    2.88
     SHOPPING
    2.70
    SHOP
    2.64
    Activations Density 0.058%

    No Known Activations