© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    library director

    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
    photograph
    -0.92
    premiere
    -0.87
    Premiere
    -0.81
    Logistics
    -0.79
    ੫
    -0.79
    Цита
    -0.78
    Hospitality
    -0.76
    Processo
    -0.76
    ϶
    -0.75
     glob
    -0.75
    POSITIVE LOGITS
     library
    4.19
     libraries
    3.55
    library
    3.14
     Library
    3.11
    Library
    2.92
     библиоте
    2.72
     Libraries
    2.67
     LIBRARY
    2.52
    LIBRARY
    2.50
     librarians
    2.48
    Activations Density 0.040%

    No Known Activations