© 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. 55739
    Prev
    Next
    INDEX
    Explanations

    defendants and legal officers

    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
    GtkWidget
    -0.90
     compares
    -0.88
    omination
    -0.88
    翼
    -0.87
    allage
    -0.87
     жерт
    -0.83
    başı
    -0.81
    っそく
    -0.79
     ля
    -0.78
     мод
    -0.78
    POSITIVE LOGITS
     defendants
    2.33
     defendant
    1.78
     Defendants
    1.47
     entities
    1.45
    defendant
    1.30
     defend
    1.21
     köy
    1.20
    Def
    1.20
     named
    1.18
    named
    1.16
    Activations Density 0.257%

    No Known Activations