© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195470
    Prev
    Next
    INDEX
    Explanations

    school districts and territories

    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_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
    设施
    0.40
     kud
    0.39
    시설
    0.39
     Kud
    0.37
     시설
    0.37
     ट्रिपल
    0.36
     uygulam
    0.36
     实
    0.36
     cult
    0.35
     çıkar
    0.35
    POSITIVE LOGITS
     districts
    1.34
     district
    1.33
    区
    1.27
     territories
    1.24
    district
    1.19
     Districts
    1.16
     zones
    1.15
     territory
    1.13
     District
    1.09
     zone
    1.09
    Activations Density 0.033%

    No Known Activations