© 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. 53958
    Prev
    Next
    INDEX
    Explanations

    code comments header files

    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
    久し
    -1.22
    お疲れ
    -1.20
    筈
    -1.18
     Others
    -1.13
    リューション
    -1.12
    Нор
    -1.09
    あっという
    -1.09
    Voor
    -1.07
     flotante
    -1.07
    お疲れ様でした
    -1.06
    POSITIVE LOGITS
    ！！！！
    1.06
     "{\"
    0.99
    &
    0.99
    が
    0.97
     „
    0.96
    sia
    0.96
    lossary
    0.94
     pady
    0.94
    緻
    0.92
     on
    0.91
    Activations Density 0.003%

    No Known Activations