© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1659
    Prev
    Next
    INDEX
    Explanations

    representing a team or entity

    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
    disposing
    -0.81
     Flüssigkeit
    -0.70
    ParallelGroup
    -0.70
    倣
    -0.70
    mut
    -0.70
    过来了
    -0.69
    (|
    -0.69
     تصميم
    -0.68
     начина
    -0.68
    プロデューサー
    -0.67
    POSITIVE LOGITS
     representing
    6.97
     represent
    6.84
    Represent
    6.25
     represents
    6.00
    代表
    5.88
     representation
    5.69
    representing
    5.66
     Representing
    5.63
     Represent
    5.50
    represent
    5.50
    Activations Density 0.345%

    No Known Activations