© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    license and sublicense

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

    plot legends and labels

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    工業
    0.46
    ılıyor
    0.46
    amentals
    0.44
     drugo
    0.44
    录
    0.44
    ("/{
    0.43
     traf
    0.42
    ^{*}$.
    0.42
    шру
    0.41
     nových
    0.41
    POSITIVE LOGITS
     HIS
    0.50
     पर्यवे
    0.47
     mensajes
    0.46
     Tans
    0.46
     தலை
    0.45
     Maintain
    0.45
     Representative
    0.45
     Glycer
    0.45
    ご利用
    0.45
     Aham
    0.44
    Activations Density 0.000%

    No Known Activations