© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10765
    Prev
    Next
    INDEX
    Explanations

    professions and specialists

    np_acts-logits-general · gemini-2.5-flash-lite

    roles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menand
    0.41
    一個人
    0.40
    ವ
    0.39
    全員
    0.38
     كلهم
    0.38
    artig
    0.38
    两个人
    0.38
    一个人
    0.38
     complemented
    0.38
    เป็นการ
    0.38
    POSITIVE LOGITS
     turned
    0.78
     Turned
    0.71
    turned
    0.62
     extraordinaire
    0.51
     specializing
    0.49
     turn
    0.46
     TURN
    0.46
     sekaligus
    0.45
     spécialiste
    0.44
     scholar
    0.44
    Activations Density 0.184%

    No Known Activations