© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31668
    Prev
    Next
    INDEX
    Explanations

    film festivals

    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_40_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
    乩
    0.42
    sparsity
    0.40
    盘
    0.40
    乐队
    0.40
    Orders
    0.39
    玩具
    0.39
    Painter
    0.38
     ผ
    0.38
    ปาก
    0.38
     painter
    0.38
    POSITIVE LOGITS
     festival
    1.05
     Festival
    0.93
    festival
    0.83
     фестива
    0.80
    Festival
    0.79
     festivals
    0.77
     fest
    0.75
     FEST
    0.75
     festiv
    0.75
     Festivals
    0.69
    Activations Density 0.002%

    No Known Activations