© 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. 60198
    Prev
    Next
    INDEX
    Explanations

    flower parts and development

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

    terminology related to flowers, plants, and plant biology.

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

    This neuron responds to botanical morphology terms, especially mentions of “petal” and related floral‐organ features.

    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
    chunk
    -0.77
    binder
    -0.77
     skin
    -0.74
    ndale
    -0.73
     bună
    -0.72
    प्त
    -0.72
    mpy
    -0.72
    esi
    -0.71
     trấn
    -0.70
    sprites
    -0.69
    POSITIVE LOGITS
     petals
    2.14
     unopened
    1.57
     buds
    1.39
     opened
    1.36
     petal
    1.35
     flower
    1.34
     corolla
    1.26
     bud
    1.25
     opening
    1.18
     flowers
    1.18
    Activations Density 0.031%

    No Known Activations