© 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. 32862
    Prev
    Next
    INDEX
    Explanations

    transported by experiences

    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
    kPa
    -0.83
    מין
    -0.78
     matern
    -0.74
    sunrise
    -0.74
    進む
    -0.73
    ogie
    -0.73
    φό
    -0.73
     gravid
    -0.71
     LNB
    -0.71
     sunrise
    -0.71
    POSITIVE LOGITS
     transport
    5.25
     transported
    4.69
    transport
    4.66
     transports
    4.53
    Transport
    4.47
     Transport
    4.41
     transporting
    4.16
     TRANSPORT
    4.03
    TRANSPORT
    3.73
     transporte
    3.56
    Activations Density 0.054%

    No Known Activations