© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 114052
    Prev
    Next
    INDEX
    Explanations

    come to mind or light

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

    The neuron consistently activates on occurrences of the word “mind” (including phrases like “comes to mind,” “crossed my mind,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </i>
    -2.23
    );
    
    -2.11
    <bos>
    -2.11
    ),
    -2.02
     {
    
    -1.80
     */
    
    -1.79
    </u>
    -1.78
    fgaben
    -1.74
    {
    -1.73
    })
    -1.69
    POSITIVE LOGITS
     unſ
    1.81
     放題
    1.75
    футболка
    1.70
    sandalia
    1.63
    Quelques
    1.59
    휀
    1.59
    Favorites
    1.55
    Passer
    1.54
    Laos
    1.49
     峰
    1.48
    Activations Density 0.004%

    No Known Activations