© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24179
    Prev
    Next
    INDEX
    Explanations

    police officers and services

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

    police and related occupations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsett
    0.51
     एग्रीकल्चर
    0.48
     enchanted
    0.48
     mago
    0.47
    産業
    0.47
     日本
    0.46
     produk
    0.45
     石
    0.45
    日本
    0.45
     Produk
    0.44
    POSITIVE LOGITS
     полицей
    1.66
     Police
    1.54
    police
    1.53
     police
    1.50
    Police
    1.48
     경찰
    1.45
     policiais
    1.45
     policing
    1.43
    警察
    1.41
     policías
    1.41
    Activations Density 0.190%

    No Known Activations