© 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. 31-GEMMASCOPE-2-RES-16K
    7. 680
    Prev
    Next
    INDEX
    Explanations

    activations

    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
    公园
    0.66
    经理
    0.64
    欢乐
    0.59
     tytu
    0.58
    woł
    0.57
     років
    0.57
    เดือน
    0.57
     东
    0.57
    爱好者
    0.57
    蛏
    0.57
    POSITIVE LOGITS
     training
    0.82
     softmax
    0.80
     output
    0.79
     torch
    0.78
     matrices
    0.77
     tensor
    0.77
     neural
    0.77
     loss
    0.76
     convolutional
    0.76
     predictions
    0.76
    Activations Density 0.591%

    No Known Activations