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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11984
    Prev
    Next
    INDEX
    Explanations

    flower, bloom, petals

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

    The neuron fires strongly on words naming flower shows, botanical displays, and related horticultural terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grundstück
    0.59
     traction
    0.57
     RPG
    0.57
    PLEX
    0.56
     CARBON
    0.56
     treadmill
    0.55
     karbon
    0.55
    炕
    0.55
     საბ
    0.55
    蹇
    0.55
    POSITIVE LOGITS
     flowers
    2.64
     flower
    2.59
     꽃
    2.47
     blooms
    2.42
    flowers
    2.36
     petals
    2.36
     Flowers
    2.34
    Flower
    2.34
    Flowers
    2.34
     Flower
    2.33
    Activations Density 0.434%

    No Known Activations