© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33594
    Prev
    Next
    INDEX
    Explanations

    plant or plant-derived products

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

    This neuron detects descriptions of botanical or plant-derived compounds, particularly when text describes what plants materials are derived from.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    小松
    -0.79
     Adop
    -0.75
     predstav
    -0.75
     adop
    -0.74
     transports
    -0.74
    Mouth
    -0.73
    Repos
    -0.73
     vase
    -0.71
     appointing
    -0.71
    柴
    -0.70
    POSITIVE LOGITS
     plants
    1.14
     растения
    1.02
     kuda
    0.93
     Endocrinology
    0.85
    原料
    0.85
     nabo
    0.83
     plantillas
    0.80
     uyt
    0.80
     klimat
    0.79
    öffentlichung
    0.79
    Activations Density 0.101%

    No Known Activations