© 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. 14534
    Prev
    Next
    INDEX
    Explanations

    agriculture, farming, farmers

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

    agriculture and farming

    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
    舰
    0.61
     contenir
    0.59
     Öffentlichkeit
    0.58
    郅
    0.58
     شخصیت
    0.57
     contentLength
    0.57
     éléments
    0.56
     tội
    0.56
     paralysie
    0.55
    律师
    0.55
    POSITIVE LOGITS
    agricultural
    2.02
     agricultural
    2.00
     farming
    1.98
    農業
    1.98
     agriculture
    1.91
    agriculture
    1.90
     agricult
    1.86
    農
    1.85
    farming
    1.84
     farmers
    1.83
    Activations Density 0.208%

    No Known Activations