Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12415
    Prev
    Next
    INDEX
    Explanations

    steel, metals, corrosion, automotive

    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_31_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
     bhikkhave
    0.55
    药物
    0.54
    婧
    0.52
    崩溃
    0.50
    幼儿园
    0.50
     grossesse
    0.49
    ప్రదేశ
    0.49
    獐
    0.48
    🍉
    0.48
    🐵
    0.48
    POSITIVE LOGITS
     steel
    1.43
     metallurgy
    1.30
     alloys
    1.29
     weld
    1.24
     steels
    1.23
     metallurgical
    1.23
     metals
    1.23
     welding
    1.21
     alloy
    1.20
    steel
    1.18
    Activations Density 0.168%

    No Known Activations