© 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. 22-GEMMASCOPE-2-RES-16K
    7. 568
    Prev
    Next
    INDEX
    Explanations

    code syntax and operations

    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
    <strong>
    0.71
    .”
    0.67
    <sup>
    0.66
     (“
    0.66
     “
    0.63
     kindred
    0.63
    often
    0.59
    ”
    0.57
    <u>
    0.56
    <em>
    0.56
    POSITIVE LOGITS
     获取
    1.63
     判断
    1.56
    调用
    1.55
    初始化
    1.53
    获取
    1.51
     初始化
    1.51
     verificar
    1.50
     调用
    1.48
     这里
    1.47
     处理
    1.45
    Activations Density 3.721%

    No Known Activations