© 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. 91647
    Prev
    Next
    INDEX
    Explanations

    users, user profiles, personnel

    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
     ProductService
    -1.05
     productName
    -1.04
     productId
    -0.98
     refreshToken
    -0.96
     locations
    -0.94
    getPost
    -0.88
     venue
    -0.87
     название
    -0.85
    ProductService
    -0.85
     getPost
    -0.84
    POSITIVE LOGITS
     person
    2.27
     Person
    1.80
     users
    1.71
     persons
    1.68
     user
    1.64
     profile
    1.59
     username
    1.55
    Person
    1.51
     personnel
    1.50
     người
    1.49
    Activations Density 0.137%

    No Known Activations