© 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. 84953
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ペン
    -0.84
    冊
    -0.84
    על
    -0.77
    ति
    -0.74
    akhir
    -0.73
    EndOf
    -0.73
     xa
    -0.72
    abend
    -0.71
     آش
    -0.70
     connections
    -0.69
    POSITIVE LOGITS
     landing
    2.02
     landings
    1.95
     invasion
    1.90
    Landing
    1.71
     Normandy
    1.65
     Landing
    1.48
     Invasion
    1.45
    invasion
    1.44
    landing
    1.43
     beaches
    1.39
    Activations Density 0.018%

    No Known Activations