© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14298
    Prev
    Next
    INDEX
    Explanations

    Dominican Republic

    np_acts-logits-general · gemini-2.5-flash-lite

    danger or negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akhir
    0.51
    lihat
    0.51
    د
    0.50
    푸
    0.49
    癲
    0.48
    کی
    0.47
    어
    0.46
    ફો
    0.45
    о
    0.45
    Lone
    0.45
    POSITIVE LOGITS
     butchers
    0.57
     HBase
    0.56
     soot
    0.56
     beech
    0.55
     bleach
    0.55
     MSD
    0.53
     chopsticks
    0.53
     linseed
    0.53
     gastronomy
    0.53
     ASH
    0.52
    Activations Density 0.009%

    No Known Activations