© 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. 116637
    Prev
    Next
    INDEX
    Explanations

    plant leaves

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

    botanical terms and plant anatomy, particularly focusing on leaves and plant parts.

    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
    findpost
    -0.83
     ബ
    -0.80
    swar
    -0.78
     hives
    -0.75
    elsch
    -0.75
     flowered
    -0.74
     cornea
    -0.73
    AssignableFrom
    -0.71
     civiles
    -0.71
     моро
    -0.71
    POSITIVE LOGITS
     leaves
    3.59
     leaf
    3.02
    leaves
    2.70
     Leaves
    2.70
    葉
    2.52
    Leaves
    2.48
     Leaf
    2.36
    leaf
    2.28
    Leaf
    2.28
    叶
    2.27
    Activations Density 0.041%

    No Known Activations