© 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. 22-GEMMASCOPE-RES-131K
    7. 84531
    Prev
    Next
    INDEX
    Explanations

    police and law enforcement

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of police or other law‐enforcement agencies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     \
    -1.09
     our
    -1.05
     ±
    -1.03
     программу
    -1.02
    вую
    -1.01
     $-$
    -1.01
     ۸
    -1.00
     juiz
    -0.98
     $\
    -0.98
     ۱۵
    -0.96
    POSITIVE LOGITS
    jelent
    1.38
     investigation
    1.16
     have
    1.13
     elementów
    1.09
     search
    1.09
     niebies
    1.08
    xspace
    1.07
     וג
    1.06
    *}[
    1.06
     communication
    1.05
    Activations Density 0.025%

    No Known Activations