© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 66648
    Prev
    Next
    INDEX
    Explanations

    LLM serving with vLLM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
     노
    0.39
     인도
    0.38
    ylar
    0.38
     효
    0.38
     사회
    0.38
     성
    0.38
    ♧
    0.37
     음식
    0.37
     에게
    0.37
     delicate
    0.36
    POSITIVE LOGITS
    実装
    0.84
    とりあえず
    0.71
    動作
    0.66
    処理
    0.60
    ディレクトリ
    0.58
    捗
    0.57
    取得
    0.57
    文字列
    0.57
    Qi
    0.57
    閾
    0.57
    Activations Density 0.005%

    No Known Activations