© 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. 82859
    Prev
    Next
    INDEX
    Explanations

    kinds of fruit

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

    references to fruits and produce in various contexts.

    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
    gafas
    -0.79
    imagens
    -0.75
     الخام
    -0.73
     equations
    -0.71
     endothelial
    -0.70
     espacios
    -0.69
    สา
    -0.69
    ament
    -0.69
    θούν
    -0.69
    ("")){
    -0.68
    POSITIVE LOGITS
     fruit
    3.80
     fruits
    3.63
    fruit
    2.55
     Fruit
    2.55
    水果
    2.53
    Fruit
    2.48
     Fruits
    2.42
     фрук
    2.41
    fruits
    2.28
     FRUIT
    2.25
    Activations Density 0.035%

    No Known Activations