© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137788
    Prev
    Next
    INDEX
    Explanations

    safety and security

    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
    Negative Logits
    Speed
    0.43
     dissolution
    0.39
    ত্ব
    0.38
    elapse
    0.38
     శరీ
    0.37
     conveyors
    0.37
    滹
    0.37
    speed
    0.37
    Ric
    0.37
    bie
    0.37
    POSITIVE LOGITS
    安全性
    0.43
     devrez
    0.42
    렘
    0.42
     安全
    0.41
     Seguro
    0.40
     Sicherheits
    0.40
     안전
    0.38
     безопасности
    0.38
     безпе
    0.38
     bezpeč
    0.38
    Activations Density 0.001%

    No Known Activations