© 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. 15904
    Prev
    Next
    INDEX
    Explanations

    social and economic classes

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

    social classes and hierarchy

    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
    专利
    0.48
     @@
    0.47
    एचओ
    0.46
    Folder
    0.45
    Bar
    0.44
     chữa
    0.44
    搭载
    0.44
     séjour
    0.44
    Rivers
    0.44
    ポ
    0.43
    POSITIVE LOGITS
     bourgeoisie
    0.84
     bourgeois
    0.75
     elites
    0.75
     intelligents
    0.65
     stratum
    0.63
     proletariat
    0.63
    वर्ग
    0.62
     class
    0.61
    educated
    0.60
     শ্রেণি
    0.60
    Activations Density 0.036%

    No Known Activations