Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8457
    Prev
    Next
    INDEX
    Explanations

    airport names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    炮
    -0.76
     solub
    -0.72
     приготовить
    -0.72
    ילום
    -0.70
     jute
    -0.70
     postman
    -0.69
     adversely
    -0.68
    Qua
    -0.68
     münd
    -0.67
     之
    -0.67
    POSITIVE LOGITS
     airport
    2.47
     airports
    2.27
     Airport
    1.97
     аэро
    1.84
    airport
    1.59
     Heathrow
    1.55
    Airport
    1.54
     فرود
    1.48
    机场
    1.48
     aeropuerto
    1.41
    Activations Density 0.067%

    No Known Activations