© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34363
    Prev
    Next
    INDEX
    Explanations

    endif preprocessor directive

    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
     to
    -1.34
    גרפיה
    -1.05
    線が
    -1.00
     Serviço
    -0.99
    礡
    -0.99
     extraordin
    -0.98
     hydrauli
    -0.96
     hotelu
    -0.96
    Ⓢ
    -0.94
     \
    -0.93
    POSITIVE LOGITS
    ană
    1.08
     trước
    1.03
    !}
    1.00
    諷
    0.99
    點擊
    0.98
     koel
    0.98
    名稱
    0.97
     înainte
    0.96
    0.94
     dokład
    0.93
    Activations Density 0.002%

    No Known Activations