© 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. 89984
    Prev
    Next
    INDEX
    Explanations

    Uganda

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

    This neuron responds to raw numerical tokens (i.e. digit sequences) appearing in data-heavy contexts.

    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
     kuan
    -1.09
    痊
    -0.93
     utaf
    -0.88
    Földrajzportál
    -0.85
     entraîner
    -0.85
    UNIFIED
    -0.84
     hina
    -0.83
     kela
    -0.83
    Tracklist
    -0.82
    idered
    -0.81
    POSITIVE LOGITS
     Uganda
    1.75
    Uganda
    1.57
     Kampala
    1.45
    🇺
    1.24
     Maker
    1.23
     Bug
    1.16
     Ugandan
    1.13
    Bug
    1.05
     Banyak
    1.04
    Kamp
    1.02
    Activations Density 0.029%

    No Known Activations