© 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. 65573
    Prev
    Next
    INDEX
    Explanations

    court cases and judges

    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
     ciclismo
    -0.83
     Jeans
    -0.79
     Perimeter
    -0.76
    StructEnd
    -0.75
     utafitiHapana
    -0.74
    ဍ
    -0.72
    spt
    -0.72
     Modus
    -0.72
    ússia
    -0.71
     Modo
    -0.71
    POSITIVE LOGITS
     court
    5.16
     courts
    5.06
     Court
    4.19
    Court
    3.80
     Courts
    3.77
    court
    3.70
    courts
    3.53
     judge
    3.33
     Supreme
    3.14
     COURT
    3.13
    Activations Density 0.187%

    No Known Activations