© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63898
    Prev
    Next
    INDEX
    Explanations

    light and brightness in multiple languages

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

    The neuron spikes on capitalized proper names—both people’s names (e.g. Svetlana, Luz Elena, Licht, Lampi) and place names (e.g. Guangxi, Puguang).

    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
    Llama
    -0.85
    リューション
    -0.85
    تما
    -0.79
    ceans
    -0.79
    ऽ
    -0.79
    抨
    -0.79
    鎰
    -0.79
    Mikhail
    -0.79
     kalian
    -0.78
    ẫu
    -0.77
    POSITIVE LOGITS
     illumination
    1.01
     illuminate
    0.94
     光
    0.92
    光
    0.91
     light
    0.91
     Licht
    0.90
    光的
    0.90
     Light
    0.89
    light
    0.88
    guang
    0.84
    Activations Density 0.017%

    No Known Activations