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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109648
    Prev
    Next
    INDEX
    Explanations

    criminal justice system participants

    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
    ifiers
    -0.83
    čios
    -0.82
     lecteur
    -0.80
     rescu
    -0.77
    馒
    -0.76
    buyer
    -0.75
    purchased
    -0.74
     schools
    -0.74
    äldrar
    -0.73
    ͏
    -0.73
    POSITIVE LOGITS
     prisoners
    1.88
     convicted
    1.77
     criminals
    1.58
     inmates
    1.49
     detainees
    1.39
     offenders
    1.38
     suspects
    1.29
     accused
    1.23
     criminal
    1.23
     prisoner
    1.12
    Activations Density 0.070%

    No Known Activations