© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11729
    Prev
    Next
    INDEX
    Explanations

    Winston Churchill, Winston-Salem

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

    tailwind css and accessibility

    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
    ERK
    0.42
    껍
    0.40
    ुम
    0.39
    atherm
    0.39
    kms
    0.39
    flex
    0.38
    ྐ
    0.38
     FLEX
    0.38
    urm
    0.38
    mien
    0.37
    POSITIVE LOGITS
     grateful
    0.46
    grateful
    0.45
     $[
    0.42
     thankful
    0.41
     geopolitical
    0.40
    -[
    0.39
    ง
    0.39
    =[
    0.38
     geo
    0.38
     Geo
    0.38
    Activations Density 0.007%

    No Known Activations