© 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. 114835
    Prev
    Next
    INDEX
    Explanations

    poverty

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

    poverty

    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
    ر
    0.60
    رش
    0.54
    re
    0.53
     earmarked
    0.52
    リ
    0.51
    روں
    0.50
    म्या
    0.50
    ר
    0.50
    ارت
    0.49
    رک
    0.49
    POSITIVE LOGITS
     poverty
    0.58
     причина
    0.55
     положение
    0.55
     상태
    0.54
     गरीबी
    0.52
     دنیا
    0.51
     स्थिति
    0.51
     परिस्थिती
    0.51
     현재
    0.50
     해결
    0.50
    Activations Density 0.009%

    No Known Activations