© 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. 34-GEMMASCOPE-RES-131K
    7. 3255
    Prev
    Next
    INDEX
    Explanations

    downtown city centers

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

    The neuron fires on tokens involved in numeric or measurement contexts—especially those indicating distances, directions, coordinates, bus routes, or times.

    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
    籍
    -0.87
    vér
    -0.78
     Takeaway
    -0.78
     Empires
    -0.77
    ς
    -0.77
    налу
    -0.75
    dados
    -0.75
     transmiti
    -0.74
     delegation
    -0.74
    (!__
    -0.74
    POSITIVE LOGITS
     downtown
    7.03
    downtown
    5.00
     Downtown
    4.91
    Downtown
    4.91
     DOWN
    2.45
     Innenstadt
    2.38
     downt
    2.31
    DOWN
    2.11
    ダウン
    2.09
     dow
    2.08
    Activations Density 0.112%

    No Known Activations