© 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. 115681
    Prev
    Next
    INDEX
    Explanations

    Ukrainian cities and regions

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

    This neuron detects named geographic entities (place names) 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
     Russian
    -0.88
     Russia
    -0.79
     rgba
    -0.74
     Parnell
    -0.71
     Hezbollah
    -0.71
    ＠
    -0.70
     كوب
    -0.70
     constructor
    -0.69
     rt
    -0.68
     construction
    -0.66
    POSITIVE LOGITS
     vyt
    0.78
     patriotism
    0.77
     ATH
    0.77
    hradun
    0.76
    IPT
    0.73
    dą
    0.73
     volunteer
    0.72
    ekwondo
    0.71
     forêt
    0.71
    کوراسیون
    0.70
    Activations Density 0.033%

    No Known Activations