© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81091
    Prev
    Next
    INDEX
    Explanations

    civil law and procedures

    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
    nitz
    -0.84
    égi
    -0.80
    êm
    -0.79
    upuk
    -0.78
    rables
    -0.77
     centimeter
    -0.75
     griega
    -0.75
     Væ
    -0.75
    iedy
    -0.73
     SDF
    -0.73
    POSITIVE LOGITS
     Civil
    2.08
    Civil
    1.86
     civil
    1.79
    civil
    1.52
     граждан
    1.29
     CIVIL
    1.25
     Civ
    1.17
     BGB
    1.15
     Código
    1.14
    民
    1.13
    Activations Density 0.013%

    No Known Activations