© 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. 103962
    Prev
    Next
    INDEX
    Explanations

    vad är Swedish? probate? VADs?

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

    The neuron activates on any token containing the letter sequence “vad” (in any context or case).

    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
     奶油
    -3.38
    鼕
    -2.88
    ）-
    -2.88
    ครื่อง
    -2.77
    quelize
    -2.73
    噚
    -2.73
    颼
    -2.72
     This
    -2.70
     Económica
    -2.67
     शुर
    -2.64
    POSITIVE LOGITS
     
    3.70
    </strong>
    3.64
    {
    3.28
    ↵
    3.13
    2
    2.89
    <i>
    2.61
    <em>
    2.56
    ↵↵
    2.52
     the
    2.50
     Acknowled
    2.48
    Activations Density 0.002%

    No Known Activations