© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63417
    Prev
    Next
    INDEX
    Explanations

    justice system and law

    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
    Not in Any Lists

    No Comments

    Negative Logits
    MARIA
    -0.96
    REMARKS
    -0.95
     Pixel
    -0.85
    öhe
    -0.84
     atrop
    -0.83
     conjugate
    -0.83
     વિ
    -0.82
    CONSUM
    -0.81
     slander
    -0.79
    спорта
    -0.79
    POSITIVE LOGITS
     incarceration
    1.35
     incarcer
    1.21
     prison
    1.19
    系统
    1.11
     prisons
    1.09
     jails
    1.08
     sentencing
    1.05
     jail
    1.02
     system
    1.02
     Prison
    0.95
    Activations Density 0.034%

    No Known Activations