© 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. 54147
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and code snippets

    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
    YNAMIC
    -1.10
    全て
    -1.02
    Clearly
    -1.01
     years
    -0.98
    古屋
    -0.98
     all
    -0.96
    жил
    -0.96
     Pastikan
    -0.96
     (
    -0.96
     но
    -0.95
    POSITIVE LOGITS
    なかな
    1.28
    我慢
    1.10
     pequena
    1.05
    Tid
    1.02
     Fähigkeiten
    1.01
     gemak
    0.99
    ły
    0.98
    Breite
    0.98
     protože
    0.97
     acestui
    0.97
    Activations Density 0.011%

    No Known Activations