© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 67
    Prev
    Next
    INDEX
    Explanations

    listing items and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    rogens
    1.03
    romeda
    1.01
    rews
    0.98
    rog
    0.97
     তারপরে
    0.95
    諧
    0.93
    ंगाबाद
    0.92
    щите
    0.91
    蔼
    0.90
     whatnot
    0.88
    POSITIVE LOGITS
    一个
    1.06
    服务
    1.06
    其他
    1.02
    小
    0.94
    小朋友
    0.80
    м
    0.79
    특별시
    0.75
    小伙伴
    0.74
     ώστε
    0.73
     edhe
    0.72
    Activations Density 1.131%

    No Known Activations