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

    Neuronpedia

    Jacobian LensNEW
    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. 1068
    Prev
    Next
    INDEX
    Explanations

    plastic and its uses

    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
     aritmética
    0.55
    礴
    0.53
     collisional
    0.52
    サーバー
    0.51
     authorizing
    0.51
    ヤモンド
    0.51
    🌗
    0.50
    集群
    0.50
    权重
    0.50
     сервер
    0.49
    POSITIVE LOGITS
     plastic
    2.48
     plastics
    2.34
     Plastics
    2.33
     Plastic
    2.28
    Plastic
    2.20
    plastic
    2.13
     plastik
    2.13
    塑料
    2.11
     प्लास्टिक
    2.09
    plastics
    2.00
    Activations Density 0.032%

    No Known Activations