© 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. 14577
    Prev
    Next
    INDEX
    Explanations

    security and safety

    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
     trad
    0.45
     vaguely
    0.45
     gợi
    0.44
     unofficial
    0.42
     vague
    0.40
     mogao
    0.40
     marketable
    0.39
     😍
    0.39
     disappointed
    0.39
     unclear
    0.39
    POSITIVE LOGITS
     safeguards
    0.94
     seguridad
    0.92
     सुरक्षा
    0.91
     keamanan
    0.91
     biztons
    0.91
     bezpiecze
    0.90
     sicurezza
    0.89
     sikker
    0.88
     segurança
    0.87
     안전
    0.86
    Activations Density 0.276%

    No Known Activations