© 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-65K
    7. 3638
    Prev
    Next
    INDEX
    Explanations

    conditionals and returns

    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_31_width_65k_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
    だけでも
    0.42
    台
    0.41
    വേ
    0.41
    अपना
    0.40
    朤
    0.40
    鿌
    0.39
    长
    0.38
    重
    0.38
     አካ
    0.37
    梂
    0.37
    POSITIVE LOGITS
     reject
    1.05
     unsuccessful
    1.05
     rejection
    1.02
     rejected
    1.02
     rejects
    1.01
     Nicht
    0.95
     rejecting
    0.94
     nicht
    0.93
     não
    0.93
     non
    0.90
    Activations Density 0.670%

    No Known Activations