© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79542
    Prev
    Next
    INDEX
    Explanations

    gluttony, finishing food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    美味しそう
    -0.91
    {?>
    -0.86
     sandwiches
    -0.85
    racia
    -0.78
     boiling
    -0.78
    ニュアル
    -0.77
     cupcakes
    -0.77
     llam
    -0.77
    手に入
    -0.77
    rant
    -0.76
    POSITIVE LOGITS
     glutton
    1.34
     finishing
    1.16
     leftovers
    1.16
     stretchy
    1.15
     stomach
    1.12
    Greedy
    1.05
    greedy
    1.05
     Greedy
    1.03
     finish
    1.02
     greedy
    1.01
    Activations Density 0.025%

    No Known Activations