© 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. 10-GEMMASCOPE-RES-131K
    7. 118754
    Prev
    Next
    INDEX
    Explanations

    vegetable names

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

    names of vegetables, particularly those from the cabbage family and green vegetables like broccoli, celery, and cauliflower.

    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_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
    鄚
    -2.55
    弢
    -2.44
    
    -2.33
    :「
    -2.30
    喼
    -2.27
     lakini
    -2.23
    嗵
    -2.20
     zey
    -2.16
    ant
    -2.13
    瞜
    -2.11
    POSITIVE LOGITS
     [
    2.41
     tomando
    2.41
    0
    2.33
     $
    2.31
     dejando
    2.19
     *
    2.11
     {
    2.11
     '
    2.06
    )
    2.05
     haciendo
    2.02
    Activations Density 0.002%

    No Known Activations