© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228709
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dept
    0.48
    むしろ
    0.44
    Former
    0.41
    Зна
    0.41
    部
    0.41
    Create
    0.40
    dept
    0.40
    ய்டா
    0.40
    存
    0.40
    สำหรับ
    0.39
    POSITIVE LOGITS
     monogram
    0.52
     ы
    0.50
     balsamic
    0.49
     influenza
    0.49
     esport
    0.48
     gols
    0.48
     Webcam
    0.47
     t
    0.47
    uccino
    0.46
     thumbnails
    0.46
    Activations Density 0.002%

    No Known Activations