© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64840
    Prev
    Next
    INDEX
    Explanations

    visual view/wave/positive/progressive

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

    The neuron fires on technical ophthalmic‐lens vocabulary—terms naming lens types or materials (e.g. bifocal, multifocal, aspheric, hydrophobic, acrylic, progressive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ){$\
    -0.74
    PHPExcel
    -0.73
    WAU
    -0.68
     ouverts
    -0.68
    𝟶
    -0.68
     pounded
    -0.67
    Tribal
    -0.66
     préférence
    -0.66
    jsoup
    -0.65
     berakhir
    -0.65
    POSITIVE LOGITS
     progres
    0.91
     progressive
    0.88
     coatings
    0.85
     coating
    0.80
     Abbe
    0.79
    尊
    0.78
    tellation
    0.78
    йтесь
    0.78
     вернуться
    0.76
     прогре
    0.76
    Activations Density 0.024%

    No Known Activations