© 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. 22-GEMMASCOPE-RES-131K
    7. 13726
    Prev
    Next
    INDEX
    Explanations

    travel and computing and cruises

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

    The neuron strongly activates on spans of promotional travel-brochure text—i.e. commercial holiday or travel package descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     new
    -1.61
     at
    -1.55
     use
    -1.55
     had
    -1.52
     work
    -1.47
     uses
    -1.44
    σιμοποι
    -1.40
    ५
    -1.38
     there
    -1.34
     other
    -1.33
    POSITIVE LOGITS
     douze
    1.71
     vrais
    1.65
     gouttes
    1.64
     délicieux
    1.63
     préférences
    1.59
     siè
    1.55
    Mengapa
    1.53
     tiroirs
    1.52
     roues
    1.50
     couverts
    1.50
    Activations Density 0.051%

    No Known Activations