© 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. 58523
    Prev
    Next
    INDEX
    Explanations

    street names

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

    The neuron activates on numeric tokens (e.g., years, street numbers, measurements).

    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
    Street
    -0.94
    Downtown
    -0.89
    England
    -0.88
     europ
    -0.85
    чен
    -0.84
     downtown
    -0.84
    人気
    -0.80
    があります
    -0.79
     Normandie
    -0.78
    postIndex
    -0.78
    POSITIVE LOGITS
     Station
    0.97
     Exchange
    0.94
     Cheap
    0.87
     Church
    0.85
     High
    0.84
     Chapel
    0.83
     Union
    0.79
     School
    0.77
     Article
    0.77
     Upper
    0.77
    Activations Density 0.036%

    No Known Activations