© 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. 34788
    Prev
    Next
    INDEX
    Explanations

    police, army, fire, courts

    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
     police
    -2.34
    police
    -2.16
     policemen
    -2.11
    Police
    -2.05
     Police
    -1.92
     policeman
    -1.89
    警察
    -1.83
     POLICE
    -1.81
     полицей
    -1.72
     पुलिस
    -1.56
    POSITIVE LOGITS
     courts
    1.08
     civilians
    1.05
     civilian
    1.04
     army
    1.02
     fire
    1.02
     court
    0.93
     prosecutors
    0.93
     other
    0.90
     judicial
    0.90
     Fire
    0.90
    Activations Density 0.026%

    No Known Activations