© 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. 39692
    Prev
    Next
    INDEX
    Explanations

    receive updates via email

    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
     but
    -1.09
     unsuccessfully
    -1.05
     But
    -1.02
    ueuse
    -1.01
     vigorously
    -1.00
     \
    -1.00
    และ
    -0.99
     finally
    -0.98
    но
    -0.96
     dianteiro
    -0.96
    POSITIVE LOGITS
     without
    1.26
     célè
    1.14
     hiç
    1.13
     melewati
    1.13
     dévelo
    1.13
     dési
    1.13
     siè
    1.12
    ☆☆☆
    1.09
     décidé
    1.09
     extré
    1.05
    Activations Density 0.014%

    No Known Activations