© 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. 47468
    Prev
    Next
    INDEX
    Explanations

    judge first and last names

    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
     Particles
    -0.81
    తా
    -0.75
    étaient
    -0.75
    валась
    -0.73
     край
    -0.73
     посмотре
    -0.72
    ඡ
    -0.72
    setColumn
    -0.72
    检测
    -0.71
     [];
    -0.71
    POSITIVE LOGITS
     judge
    2.19
     Judge
    2.03
    Judge
    1.94
    judge
    1.59
     judges
    1.59
     JUDGE
    1.56
     Judges
    1.41
    Judges
    1.26
    JUDGE
    1.24
     sentencing
    1.23
    Activations Density 0.175%

    No Known Activations