© 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. 117812
    Prev
    Next
    INDEX
    Explanations

    police or fire departments

    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
    üdis
    -0.87
    omyelitis
    -0.83
    uyer
    -0.82
    EnumMember
    -0.82
     superintendents
    -0.80
    んな
    -0.79
     thrombosis
    -0.79
    igten
    -0.78
    affichage
    -0.78
    ferencia
    -0.77
    POSITIVE LOGITS
     department
    1.75
     Department
    1.52
    department
    1.50
    Department
    1.33
     departments
    1.10
    DEPARTMENT
    1.09
     DEPARTMENT
    1.02
     Dept
    0.98
    departments
    0.95
     dept
    0.94
    Activations Density 0.018%

    No Known Activations