© 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. 98135
    Prev
    Next
    INDEX
    Explanations

    law enforcement operations and targeting

    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
     conflicts
    -0.81
     bullets
    -0.81
     terrorist
    -0.79
     disputes
    -0.78
     defence
    -0.77
    閉じ
    -0.75
     cucharadas
    -0.75
    vä
    -0.74
    DISTANCE
    -0.74
    iços
    -0.73
    POSITIVE LOGITS
     targeted
    1.30
     crackdown
    1.26
     targeting
    1.23
     enforcement
    1.19
     saturation
    1.19
    enforcement
    1.14
    targeted
    1.14
     Schwerpunkt
    1.10
    Saturation
    1.10
     blitz
    1.09
    Activations Density 0.018%

    No Known Activations