© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8886
    Prev
    Next
    INDEX
    Explanations

    Big followed by common nouns

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

    big, big picture, big commerce

    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
    X
    0.63
    A
    0.56
     large
    0.54
    Large
    0.50
    R
    0.46
    एक्स
    0.46
    ل
    0.45
    anı
    0.44
    Amounts
    0.44
    大型
    0.44
    POSITIVE LOGITS
    big
    1.08
     BIG
    1.02
    Big
    0.97
     Big
    0.96
    BIG
    0.90
     big
    0.86
     বিগ
    0.81
     빅
    0.80
     बिग
    0.77
    빅
    0.77
    Activations Density 0.071%

    No Known Activations