Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52776
    Prev
    Next
    INDEX
    Explanations

    aspect, degree, situation

    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_29_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
    里的
    1.12
    裡的
    0.92
    科技
    0.88
    里
    0.86
    中的
    0.84
    șt
    0.79
    里面的
    0.79
    组
    0.79
    ပေါင်း
    0.78
    资源
    0.77
    POSITIVE LOGITS
    မှု
    1.05
     terhadap
    1.04
    ness
    1.02
    而在
    1.02
    而
    1.00
     situasi
    0.96
     while
    0.96
    성에
    0.94
    while
    0.94
     serta
    0.94
    Activations Density 0.007%

    No Known Activations