© 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. 58443
    Prev
    Next
    INDEX
    Explanations

    online services and products

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

    The neuron strongly activates on commercial and promotional keywords—brand or product names and action terms like “order,” “buy,” “download,” “online,” or “delivery”—marking e-commerce/ad text.

    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
     respetu
    -0.85
    allets
    -0.83
     senderismo
    -0.79
     ihn
    -0.78
    PageData
    -0.76
    ライズ
    -0.75
    ôt
    -0.75
    blest
    -0.75
    生态
    -0.74
    DisplayMode
    -0.74
    POSITIVE LOGITS
     door
    1.01
     doors
    0.92
    ριθ
    0.87
     in
    0.86
     delivered
    0.81
     telephones
    0.81
     shipped
    0.80
    Associazione
    0.78
    Посилання
    0.76
     รูป
    0.75
    Activations Density 0.005%

    No Known Activations