© 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. 17-GEMMASCOPE-2-RES-16K
    7. 16126
    Prev
    Next
    INDEX
    Explanations

    pinyin and chinese

    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_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
    Como
    0.88
    Wenn
    0.79
     Como
    0.79
    Kuch
    0.78
     Chancen
    0.77
     Gibt
    0.77
    𝗶
    0.76
    pana
    0.75
     Jin
    0.75
    𝘁
    0.74
    POSITIVE LOGITS
     cyclin
    0.71
    的选择
    0.65
    混合
    0.64
    必需
    0.63
    任
    0.63
     由
    0.63
     correlated
    0.62
    运行
    0.62
    用
    0.60
    决定
    0.60
    Activations Density 0.013%

    No Known Activations