© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 155
    Prev
    Next
    INDEX
    Explanations

    saving face

    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_all/layer_41_width_262k_l0_big
    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
    ผลิตภัณฑ์
    0.58
     carénés
    0.54
    產品
    0.53
    itumor
    0.53
    數據
    0.52
    閾
    0.52
    繁忙時間
    0.49
     ആദ്യ
    0.47
    創新
    0.46
    格納
    0.46
    POSITIVE LOGITS
    吃
    0.55
     scolded
    0.47
     Ghost
    0.46
     잡
    0.45
    骂
    0.45
     pat
    0.45
     gossip
    0.45
     Face
    0.44
     slap
    0.44
     get
    0.44
    Activations Density 0.005%

    No Known Activations