© 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. 6931
    Prev
    Next
    INDEX
    Explanations

    setting up

    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
    5
    -1.03
    3
    -0.98
     élas
    -0.97
    孕妇
    -0.95
     walt
    -0.94
     sellado
    -0.91
    Inser
    -0.90
    8
    -0.89
     solidif
    -0.88
    有個
    -0.85
    POSITIVE LOGITS
     shop
    1.80
     for
    1.34
    shop
    1.24
     a
    1.23
     appointments
    1.16
     operations
    1.13
     setup
    1.11
     infrastructure
    1.09
     arrangements
    1.08
     Shop
    1.07
    Activations Density 0.022%

    No Known Activations