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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3699
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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_22_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
     left
    1.28
    left
    1.12
     Left
    1.08
    Left
    1.05
    LEFT
    1.00
     LEFT
    0.99
     leaving
    0.97
    左
    0.81
     Leaving
    0.79
     왼쪽
    0.77
    POSITIVE LOGITS
     corredor
    0.97
    Ё
    0.86
     المتع
    0.85
     telur
    0.83
     meng
    0.83
     temiz
    0.82
     vontade
    0.82
     voluntad
    0.82
    פול
    0.81
     বাসন
    0.81
    Activations Density 0.159%

    No Known Activations