© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27342
    Prev
    Next
    INDEX
    Explanations

    discord bots and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    认
    0.44
    า
    0.44
    訊息
    0.40
    내가
    0.39
     swo
    0.39
     sender
    0.38
     구독
    0.38
     subnet
    0.37
    昴
    0.37
    站
    0.37
    POSITIVE LOGITS
    Discord
    0.54
     Botswana
    0.52
     Discord
    0.51
     discord
    0.49
    Bots
    0.49
     Bots
    0.48
    bots
    0.48
    BOT
    0.45
     тү
    0.44
     Concord
    0.43
    Activations Density 0.005%

    No Known Activations