© 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. 29902
    Prev
    Next
    INDEX
    Explanations

    habeas corpus petitions

    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
     LIABILITY
    -0.79
     Clough
    -0.77
    PLAINT
    -0.74
    quad
    -0.73
    ⎕
    -0.73
     waterproof
    -0.72
     acetone
    -0.67
     plaintiff
    -0.67
    舛
    -0.67
     espoir
    -0.67
    POSITIVE LOGITS
     habeas
    1.75
    habe
    1.34
     Habe
    1.23
     AED
    1.14
    AED
    1.13
     prisoners
    0.98
     petitioner
    0.96
    Habe
    0.95
     relief
    0.93
     inmate
    0.89
    Activations Density 0.127%

    No Known Activations