© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4612
    Prev
    Next
    INDEX
    Explanations

    farming and agriculture terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    bies
    1.86
     undersea
    1.76
    ཾ
    1.71
     ими
    1.71
     사항
    1.70
    மைப்பு
    1.68
     métro
    1.65
    ینگ
    1.65
    स्तू
    1.65
    ள்க
    1.63
    POSITIVE LOGITS
     agricole
    2.56
     Farming
    2.53
    耕
    2.39
    Agricult
    2.37
     agrícolas
    2.34
     agricult
    2.34
     agrícola
    2.31
    作物
    2.30
    agro
    2.25
     agric
    2.24
    Activations Density 1.246%

    No Known Activations