© 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. 102531
    Prev
    Next
    INDEX
    Explanations

    applaud or welcome

    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
    esía
    -0.81
    ogenesis
    -0.81
    доста
    -0.80
     apologise
    -0.80
    שוב
    -0.77
    ง่าย
    -0.77
     lohnt
    -0.75
     refuses
    -0.74
    iar
    -0.74
    다는
    -0.74
    POSITIVE LOGITS
     welcome
    3.81
     welcomed
    3.53
     welcomes
    3.05
     applaud
    2.89
    welcome
    2.78
     welcoming
    2.73
     appla
    2.56
     Welcome
    2.53
     applauded
    2.44
    Welcome
    2.39
    Activations Density 0.048%

    No Known Activations