© 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. 50383
    Prev
    Next
    INDEX
    Explanations

    software copyright notices

    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
     призна
    -0.89
     wallet
    -0.87
    isbn
    -0.85
    SHOP
    -0.77
     Freitag
    -0.75
     Saison
    -0.73
     saison
    -0.72
    SAFE
    -0.70
     temporada
    -0.68
     năm
    -0.68
    POSITIVE LOGITS
    tracker
    0.97
     trackers
    0.93
     tracker
    0.91
     psychedelic
    0.91
     Tracker
    0.90
    Յ
    0.90
     collab
    0.88
    rót
    0.86
    Tracker
    0.86
     XM
    0.83
    Activations Density 0.073%

    No Known Activations