© 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. 33537
    Prev
    Next
    INDEX
    Explanations

    Miami Florida

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

    The neuron primarily detects numeric tokens—any standalone numbers or digit sequences in the text.

    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
     encan
    -0.79
    囔
    -0.77
     набор
    -0.77
     bargaining
    -0.74
     banner
    -0.74
    Vend
    -0.74
     Datenschutzer
    -0.73
     Islamic
    -0.73
     insulating
    -0.73
     wykorzyst
    -0.72
    POSITIVE LOGITS
    Miami
    1.56
     Miami
    1.49
     miami
    1.45
     Broward
    1.43
    mdb
    1.40
    miami
    1.27
    MDB
    1.19
     Everglades
    1.13
     Dade
    1.06
     Meeres
    1.02
    Activations Density 0.001%

    No Known Activations