© 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. 244967
    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
     literary
    0.43
     dist
    0.42
    綫
    0.42
    สู่
    0.42
    Raj
    0.42
    Fed
    0.41
    Global
    0.40
     mergers
    0.40
     powers
    0.40
     heapq
    0.40
    POSITIVE LOGITS
     有
    0.52
     Че
    0.49
     Fortunately
    0.47
     茶
    0.45
     tibia
    0.45
    有一個
    0.45
     Germain
    0.44
     attrakt
    0.44
     Rezept
    0.43
     І
    0.43
    Activations Density 0.002%

    No Known Activations