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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27105
    Prev
    Next
    INDEX
    Explanations

    plants and botany

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     προσωπ
    0.52
     мясо
    0.52
     사회
    0.50
     ஓடுப
    0.50
     rheumat
    0.50
     crossbody
    0.50
    颞
    0.49
    個人的
    0.48
     социального
    0.48
     肩
    0.47
    POSITIVE LOGITS
     पौधे
    1.00
    Plants
    1.00
     Plants
    0.99
     plants
    0.96
    植物
    0.93
     растение
    0.92
     plant
    0.91
     xylem
    0.89
     растения
    0.85
     piante
    0.84
    Activations Density 0.161%

    No Known Activations