© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1385
    Prev
    Next
    INDEX
    Explanations

    list indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    意识
    0.88
    创造
    0.78
    性
    0.77
    真正
    0.76
    性的
    0.76
    一部
    0.74
    争取
    0.73
    随
    0.72
    表面
    0.71
    固
    0.70
    POSITIVE LOGITS
     кг
    1.12
     на
    1.10
     અને
    1.07
     على
    1.04
     француз
    1.03
     من
    1.03
     ك
    1.03
     recursively
    1.02
     дерева
    1.01
     рублей
    1.01
    Activations Density 0.010%

    No Known Activations