© 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. 62624
    Prev
    Next
    INDEX
    Explanations

    kingdom and heaven

    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
     pys
    -0.78
     apache
    -0.76
     シャンプー
    -0.75
    大統領
    -0.71
     sevilla
    -0.69
    certified
    -0.69
    }*/
    -0.65
     cactus
    -0.65
     globally
    -0.65
    utus
    -0.65
    POSITIVE LOGITS
     kingdom
    4.72
     Kingdom
    4.50
    Kingdom
    3.66
    kingdom
    3.53
     KINGDOM
    2.95
     kingdoms
    2.64
     reino
    2.44
     Kingdoms
    2.33
    王国
    1.98
     Reino
    1.91
    Activations Density 0.029%

    No Known Activations