© 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. 70621
    Prev
    Next
    INDEX
    Explanations

    onion, garlic

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

    food ingredients commonly used in cooking, especially alliums like onion, garlic, and shallots.

    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
     dergleichen
    -2.50
    ”,
    -2.48
    .”
    -2.41
    A
    -2.41
    </
    -2.25
    ,’’
    -2.17
    ,”
    -2.16
    {
    -2.14
    :”
    -2.14
     selben
    -2.11
    POSITIVE LOGITS
    ⎆
    2.05
    ación
    1.95
     We
    1.92
     fortitude
    1.84
     Slovensku
    1.81
    ции
    1.81
    ются
    1.80
     \"
    1.77
     knihy
    1.76
    虓
    1.76
    Activations Density 0.006%

    No Known Activations