© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    bottom line

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

    bottom up, bottom of, bottom right, bottom line

    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
     TOP
    0.50
    TOP
    0.43
     Conditioner
    0.42
    頂
    0.41
     INDUSTRY
    0.41
     normativa
    0.41
    يه
    0.39
     top
    0.39
    वाहिक
    0.39
     topp
    0.39
    POSITIVE LOGITS
     bottom
    0.80
    Bottom
    0.75
     Bottom
    0.73
    底
    0.73
     bottoms
    0.71
     đáy
    0.71
    bottom
    0.70
    底部
    0.61
     底
    0.61
    BOTTOM
    0.53
    Activations Density 0.068%

    No Known Activations