© 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. 58057
    Prev
    Next
    INDEX
    Explanations

    saying hello or goodbye

    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
     bid
    -1.79
    Bid
    -1.39
     bidding
    -1.38
     bids
    -1.31
    bid
    -1.26
     Bid
    -1.18
     Bids
    -1.16
    Bidding
    -1.13
     bade
    -1.13
     Bidding
    -1.10
    POSITIVE LOGITS
     goodbye
    3.13
     farewell
    2.13
    goodbye
    1.80
     Goodbye
    1.76
    Goodbye
    1.70
     bye
    1.59
     good
    1.57
     hello
    1.45
    hello
    1.27
    bye
    1.20
    Activations Density 0.014%

    No Known Activations