© 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. 98324
    Prev
    Next
    INDEX
    Explanations

    a complicated selector

    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
    ’，
    -2.88
    in
    -2.81
    le
    -2.78
    鹮
    -2.50
    la
    -2.48
    のが
    -2.39
    ± 
    -2.36
    現在は
    -2.28
     excessively
    -2.25
     arduous
    -2.22
    POSITIVE LOGITS
    értel
    2.17
     you
    1.99
    鰱
    1.98
     parfois
    1.93
    いい
    1.90
     взаимодействия
    1.85
     بدأ
    1.85
    ностях
    1.84
     разные
    1.84
    を選択
    1.83
    Activations Density 0.200%

    No Known Activations