© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105597
    Prev
    Next
    INDEX
    Explanations

    flower and floral descriptions

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

    words and phrases related to flowers and floral elements.

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

    The neuron primarily detects mentions of “flower” and its close variants (e.g. floral, flowers, flowering).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ta
    -2.14
    ).
    -1.95
    塒
    -1.82
    ()){
    
    -1.80
    ti
    -1.80
    на
    -1.69
    so
    -1.66
    ();
    -1.66
    ❉
    -1.64
    ји
    -1.61
    POSITIVE LOGITS
    ]
    2.61
     verkau
    1.87
     preciosas
    1.80
     ajustado
    1.79
     retirado
    1.77
     raras
    1.73
     vorigen
    1.71
     coloridas
    1.71
     delicado
    1.69
     buscando
    1.67
    Activations Density 0.029%

    No Known Activations