© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117904
    Prev
    Next
    INDEX
    Explanations

    low cost airlines

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

    The neuron strongly activates on tokens that are part of named entities (especially organization or airline names) in news‐wire 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
    hika
    -0.77
     Shiba
    -0.75
    ospel
    -0.75
     Tear
    -0.75
    resnet
    -0.72
    малар
    -0.72
     suction
    -0.71
    Tear
    -0.70
    élection
    -0.70
     jajaran
    -0.68
    POSITIVE LOGITS
     low
    1.63
     cheap
    1.47
     budget
    1.43
     discount
    1.41
    budget
    1.16
    廉
    1.15
    discount
    1.14
     Discount
    1.13
    Discount
    1.13
    Budget
    1.12
    Activations Density 0.022%

    No Known Activations