© 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. 22-GEMMASCOPE-RES-131K
    7. 39414
    Prev
    Next
    INDEX
    Explanations

    Category:

    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_22/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
     all
    -1.14
     توانند
    -1.02
     any
    -0.93
     for
    -0.91
     remain
    -0.90
    
    -0.89
     procedures
    -0.88
    人を
    -0.87
    šia
    -0.87
     venons
    -0.86
    POSITIVE LOGITS
    っているので
    1.10
    即是
    1.01
    cheon
    1.00
     WITHIN
    1.00
    Decry
    0.99
    zyme
    0.98
    cbf
    0.96
    掠
    0.96
     несколько
    0.95
     ولی
    0.94
    Activations Density 0.015%

    No Known Activations