© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    US government and military affairs

    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
    简单
    0.85
    辂
    0.82
     Canva
    0.80
    丽
    0.79
    柅
    0.79
    景观
    0.78
    纹
    0.77
    营养
    0.76
    濑
    0.75
     previewBuilder
    0.74
    POSITIVE LOGITS
    military
    1.21
    軍
    1.20
     military
    1.18
     NATO
    1.16
    political
    1.16
    strategic
    1.14
     diplomatic
    1.12
     political
    1.09
     diplomats
    1.09
     Afghanistan
    1.07
    Activations Density 0.154%

    No Known Activations