© 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-262K
    7. 211801
    Prev
    Next
    INDEX
    Explanations

    Prussian Army and Adam Smith

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

    other State

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     &
    0.56
     입니다
    0.53
     উভ
    0.52
     briefly
    0.52
     बेहद
    0.51
     Briefly
    0.51
     Viewing
    0.51
     ترین
    0.50
    叧
    0.50
     গুলো
    0.50
    POSITIVE LOGITS
     moneys
    0.55
     diminution
    0.55
     prosecutions
    0.55
     speculators
    0.55
    க்கூடிய
    0.55
     disgraceful
    0.54
     treatises
    0.54
    そういう
    0.54
    гази
    0.54
     injustice
    0.54
    Activations Density 0.006%

    No Known Activations