© 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. 48437
    Prev
    Next
    INDEX
    Explanations

    fragments

    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
    塤
    -2.06
    
    -1.93
    特長
    -1.91
     traduce
    -1.78
     置物
    -1.78
     appris
    -1.78
    Ᏺ
    -1.75
    焄
    -1.73
    鏨
    -1.73
    lardan
    -1.72
    POSITIVE LOGITS
     is
    2.53
    (
    2.13
     $\
    2.13
    ”
    1.88
    \
    1.73
    而后
    1.72
    O
    1.66
     now
    1.66
     or
    1.61
     $
    1.60
    Activations Density 0.011%

    No Known Activations