© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    prisoners, captives, liberty

    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
     its
    -0.79
    laga
    -0.78
     uninstalled
    -0.76
    床上
    -0.75
     parle
    -0.72
     Phone
    -0.71
    蜱
    -0.70
    swf
    -0.69
     eloku
    -0.69
    calvin
    -0.69
    POSITIVE LOGITS
     captives
    1.07
     prisoners
    1.04
     broken
    0.98
     liberty
    0.90
     Prisoners
    0.89
     downt
    0.88
    Prison
    0.82
    broken
    0.81
     Inhalts
    0.81
     captive
    0.80
    Activations Density 0.007%

    No Known Activations