© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1260
    Prev
    Next
    INDEX
    Explanations

    pipeline equipment leak detection

    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
    DeviceCompliance
    0.61
    情节
    0.61
    剧情
    0.59
     shameful
    0.59
     じゃん
    0.58
    民间
    0.57
    隐私
    0.56
    觎
    0.56
    行动
    0.56
     dystopian
    0.55
    POSITIVE LOGITS
     equipment
    0.80
     steel
    0.80
     flanges
    0.79
     corrosion
    0.78
     flange
    0.78
     weld
    0.76
     feedwater
    0.76
     hydraul
    0.76
     hydraulic
    0.75
     nozzles
    0.74
    Activations Density 0.364%

    No Known Activations