© 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. 93799
    Prev
    Next
    INDEX
    Explanations

    joining or leaving teams

    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
     tackled
    -0.84
     обрабаты
    -0.83
    래스
    -0.81
    予約
    -0.79
     udrž
    -0.78
    InView
    -0.76
    tivazione
    -0.76
    鏡
    -0.75
     {:.
    -0.75
     nẵng
    -0.75
    POSITIVE LOGITS
     destination
    1.23
     joining
    1.17
     reunion
    1.14
     destinations
    1.13
     loyalty
    1.09
     teams
    1.09
     team
    1.09
     landing
    1.06
    Affiliation
    1.05
    destination
    1.04
    Activations Density 0.039%

    No Known Activations