© 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. 87099
    Prev
    Next
    INDEX
    Explanations

    oats, oatmeal, porridge, bran

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

    This neuron detects references to oats and oat‐based foods (e.g., oatmeal or porridge).

    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
    ごめんなさい
    -1.76
    鵄
    -1.75
    すみません
    -1.66
    ⡪
    -1.63
     vorige
    -1.62
    dı
    -1.59
     gekocht
    -1.58
    たまに
    -1.57
    "}}
    -1.55
    
    -1.55
    POSITIVE LOGITS
    '
    2.00
     When
    1.95
     Only
    1.71
    $
    1.69
    z
    1.59
    ）
    1.48
     How
    1.46
    ,”
    1.45
    美女
    1.44
     ….
    1.42
    Activations Density 0.014%

    No Known Activations