© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39645
    Prev
    Next
    INDEX
    Explanations

    locations following "in"

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

    The neuron spikes on the word “in” when it’s used to introduce a city/state location (e.g. “in Nashville, Tennessee,” “in La Marque, TX,” 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_10/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
     a
    -1.41
    着一
    -1.30
    着一个
    -1.30
     two
    -1.27
     “
    -1.26
    —”
    -1.25
    expédition
    -1.23
     after
    -1.23
    woners
    -1.23
     when
    -1.21
    POSITIVE LOGITS
     nuevo
    1.32
     nuevos
    1.30
    Beskrivning
    1.28
    给我们
    1.22
     nueva
    1.21
     who
    1.21
    
    1.21
    kswagen
    1.20
     nieuwe
    1.20
     этаж
    1.18
    Activations Density 0.085%

    No Known Activations