© 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. 40366
    Prev
    Next
    INDEX
    Explanations

    airports and ports and their locations

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

    the presence of numeric expressions (quantities, measurements, distances, etc.)

    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
     изменить
    -1.04
     durante
    -1.02
     perſ
    -0.98
     ALLOWED
    -0.98
     vreme
    -0.95
     medes
    -0.94
    はじめに
    -0.92
    pée
    -0.91
    addCriterion
    -0.91
    \|_{
    -0.91
    POSITIVE LOGITS
     airport
    1.16
     nearest
    1.02
     on
    0.97
     airports
    0.97
     in
    0.96
     distance
    0.91
    Approximate
    0.88
     then
    0.85
     varandra
    0.85
     from
    0.82
    Activations Density 0.013%

    No Known Activations