© 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. 31-GEMMASCOPE-2-RES-65K
    7. 3845
    Prev
    Next
    INDEX
    Explanations

    conquests and territorial changes

    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
    每个
    0.72
     Produkte
    0.71
    波动
    0.69
     Canva
    0.68
    槑
    0.68
    研发
    0.66
    消费者
    0.66
    珵
    0.65
     ஆரோக்கிய
    0.64
     产品
    0.64
    POSITIVE LOGITS
     negotiations
    0.63
     victorious
    0.62
     raids
    0.61
     diplomatic
    0.58
     tropas
    0.57
     troops
    0.56
     exiled
    0.56
     east
    0.55
     invasion
    0.55
    campaign
    0.55
    Activations Density 0.082%

    No Known Activations