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. 17-GEMMASCOPE-2-RES-65K
    4. 1808
    Prev
    Next
    INDEX
    Explanations

    code keywords and data types

    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_17_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
    ↵↵
    0.74
     famously
    0.73
    auf
    0.73
    us
    0.71
    riving
    0.70
     microbi
    0.69
    horm
    0.69
    this
    0.68
     physiologically
    0.68
    をもって
    0.68
    POSITIVE LOGITS
     类型
    0.77
    删除
    0.77
    序号
    0.76
     `=`,
    0.75
     종류
    0.72
     `:`,
    0.71
    爣
    0.70
    字段
    0.70
     Rectangle
    0.70
     '*',
    0.70
    Activations Density 0.896%

    No Known Activations