© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107628
    Prev
    Next
    INDEX
    Explanations

    authentic and traditional experiences

    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
    vereign
    -0.90
    namental
    -0.87
     zk
    -0.84
    надцать
    -0.80
    DispatchQueue
    -0.79
    ogues
    -0.79
     аккумулятор
    -0.79
     exigencias
    -0.79
    ultas
    -0.79
    舶
    -0.79
    POSITIVE LOGITS
     authentic
    1.52
    AUTHENT
    1.34
     local
    1.28
    Authentic
    1.24
     village
    1.23
     traditional
    1.23
     locals
    1.23
    authentic
    1.15
     authenticity
    1.15
    ชาว
    1.14
    Activations Density 0.022%

    No Known Activations