© 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-65K
    7. 48940
    Prev
    Next
    INDEX
    Explanations

    safe / safely

    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_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
    ิทธิภาพ
    0.45
    лм
    0.38
    𒈦
    0.37
    ▄
    0.37
    رود
    0.37
    мих
    0.37
    ঙ্ঘ
    0.36
    憔
    0.36
    emplo
    0.35
     অবধি
    0.35
    POSITIVE LOGITS
     safe
    3.45
     safely
    3.23
    safe
    3.13
    Safe
    3.06
     Safe
    3.03
     безопас
    3.02
     bezpie
    2.88
     सुरक्षित
    2.77
     safer
    2.70
    安全的
    2.64
    Activations Density 0.239%

    No Known Activations