© 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. 118384
    Prev
    Next
    INDEX
    Explanations

    flying and arriving

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

    The neuron activates on words and phrases describing travel or movement, particularly air travel (e.g., flew, jet, arriving, headed).

    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
    ੯
    -0.88
     both
    -0.82
    ://
    -0.82
    属性
    -0.81
    ندما
    -0.79
    ₫
    -0.79
    wardship
    -0.77
    kå
    -0.77
     Brems
    -0.75
    八年
    -0.74
    POSITIVE LOGITS
     flight
    2.86
     flights
    2.42
     flying
    2.41
     flew
    2.30
    flight
    2.25
     plane
    2.19
     Flight
    2.17
     flown
    2.16
     airports
    2.16
     airport
    2.14
    Activations Density 0.045%

    No Known Activations