© 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. 10-GEMMASCOPE-RES-131K
    7. 29066
    Prev
    Next
    INDEX
    Explanations

    real and imaginary parts

    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_10/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
    摀
    -2.47
    跸
    -2.03
    裢
    -1.98
    糁
    -1.97
    ⸨
    -1.97
    鲞
    -1.95
     conclud
    -1.91
    ཥ
    -1.88
    厛
    -1.88
    
    -1.83
    POSITIVE LOGITS
    2
    2.67
    0
    2.64
    1
    2.28
    8
    2.11
     at
    2.11
    e
    2.02
    3
    1.94
     undeniably
    1.88
    '
    1.87
     EVERY
    1.83
    Activations Density 0.009%

    No Known Activations