© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107761
    Prev
    Next
    INDEX
    Explanations

    TV box Roku

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

    The neuron is triggered by mentions of specific electronic hardware product names or models.

    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
     मोबाइल
    -0.77
     AMOLED
    -0.75
     bater
    -0.70
    createCell
    -0.69
    酚
    -0.69
    smartphone
    -0.69
    cznie
    -0.69
    쭉
    -0.68
    RFID
    -0.67
    手机
    -0.66
    POSITIVE LOGITS
     boxes
    1.63
     box
    1.53
     Boxes
    1.41
     Box
    1.41
     Roku
    1.30
    Boxes
    1.28
    Box
    1.28
    box
    1.27
    boxes
    1.27
    BOX
    1.25
    Activations Density 0.053%

    No Known Activations