© 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. 60023
    Prev
    Next
    INDEX
    Explanations

    private member fields

    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
    puesto
    -0.75
     naselje
    -0.73
     entlang
    -0.73
    ходе
    -0.73
     DriverManager
    -0.73
     întâ
    -0.72
    函数
    -0.72
    ль
    -0.72
     함수
    -0.72
    zać
    -0.71
    POSITIVE LOGITS
     fields
    2.78
     field
    2.44
     member
    2.36
     members
    2.27
    成员
    2.22
     private
    2.16
    fields
    2.16
    Fields
    2.14
     Fields
    2.06
     FIELDS
    1.95
    Activations Density 0.125%

    No Known Activations