© 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. 61393
    Prev
    Next
    INDEX
    Explanations

    dialog box messages

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

    The neuron fires on code tokens that invoke dialog‐display methods (e.g. MessageBox.Show, ShowDialog, etc.).

    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
    ,\\
    -1.72
    -\\
    -1.59
     a
    -1.59
    汌
    -1.50
     explicado
    -1.48
    </h2>
    -1.45
    ⚋
    -1.43
     aiding
    -1.37
    </h5>
    -1.36
     slated
    -1.36
    POSITIVE LOGITS
    0
    1.76
    *
    1.68
    蔸
    1.65
    ве
    1.64
    .
    1.59
    5
    1.58
    栳
    1.56
     что
    1.55
     possibility
    1.55
     типа
    1.55
    Activations Density 0.001%

    No Known Activations