© 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. 80012
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    reaching
    -1.09
    typical
    -1.07
     normalerweise
    -1.01
    却不
    -1.00
    менять
    -0.99
     aw
    -0.98
     Nineteenth
    -0.96
    extended
    -0.95
     Sunni
    -0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.93
    POSITIVE LOGITS
     before
    1.65
     comparison
    1.44
     Before
    1.39
     after
    1.37
     measurements
    1.27
     baseline
    1.27
     October
    1.20
     January
    1.20
     July
    1.19
     measurement
    1.18
    Activations Density 0.147%

    No Known Activations