© 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. 572
    Prev
    Next
    INDEX
    Explanations

    parts of plants

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

    plant parts and anatomical structures in scientific/botanical descriptions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on Latin botanical names (genus + species) of plants.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    cashire
    -0.82
    entreprises
    -0.80
    planted
    -0.79
     geçir
    -0.72
     társ
    -0.71
    ツリー
    -0.68
    Squid
    -0.68
     خاط
    -0.68
    lugin
    -0.68
     Aufenthalts
    -0.68
    POSITIVE LOGITS
     leaves
    3.02
     flowers
    2.45
     leaf
    2.03
    leaves
    2.00
     Leaves
    1.95
     fruits
    1.92
     seeds
    1.80
    Leaves
    1.78
     foliage
    1.70
     fruit
    1.66
    Activations Density 0.115%

    No Known Activations