© 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. 81032
    Prev
    Next
    INDEX
    Explanations

    Spring Bean and beanstalk

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

    The neuron activates for the word "Bean" or "bean" in various contexts, particularly in programming or technology-related content.

    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
     dianteira
    -0.93
     markiert
    -0.88
     serdecznie
    -0.88
     químicos
    -0.81
     entwick
    -0.81
    過的
    -0.81
    และ
    -0.80
    デメリット
    -0.78
    あんまり
    -0.77
    司机
    -0.77
    POSITIVE LOGITS
    stalk
    1.45
    Bean
    1.15
    getBean
    1.13
     Bean
    1.04
     curd
    1.01
    From
    1.00
    Pod
    0.99
    bean
    0.98
     bean
    0.88
    eterminate
    0.88
    Activations Density 0.006%

    No Known Activations