© 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. 93567
    Prev
    Next
    INDEX
    Explanations

    delivery confirmation and tracking

    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
    EOUT
    -0.79
     unqualified
    -0.78
    uke
    -0.77
    Rounded
    -0.77
     自
    -0.75
    ِّ
    -0.75
    같이
    -0.75
    воря
    -0.73
    unger
    -0.73
     pane
    -0.73
    POSITIVE LOGITS
     tracking
    1.16
    Tracking
    1.02
     signature
    1.01
     Tracking
    1.00
    tracking
    0.96
     delivery
    0.93
     receipt
    0.82
     Delivery
    0.81
    Gambas
    0.80
     confirmation
    0.79
    Activations Density 0.038%

    No Known Activations