© 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. 53-GEMMASCOPE-2-RES-262K
    7. 18642
    Prev
    Next
    INDEX
    Explanations

    offensive assaults and invasion

    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_53_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
     الناتج
    0.42
    事故
    0.41
     kejadian
    0.40
    葩
    0.39
     accidente
    0.38
    బ్బు
    0.38
    较低
    0.38
    Malcolm
    0.38
    事件
    0.38
    洒
    0.38
    POSITIVE LOGITS
     offensive
    1.43
     offens
    1.30
     Offensive
    1.20
     ofens
    1.20
    offensive
    1.09
     assault
    1.05
     assaults
    0.96
     offensively
    0.91
     offense
    0.89
     coordinated
    0.89
    Activations Density 0.024%

    No Known Activations