© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91870
    Prev
    Next
    INDEX
    Explanations

    Danube river valley

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

    This neuron detects numerical data entries—especially numeric values and related units—in geographic infoboxes.

    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
     Harz
    -0.90
     Tasmanian
    -0.79
    Alec
    -0.78
     gyerme
    -0.76
     začet
    -0.73
    Pine
    -0.73
    Wyoming
    -0.72
     Pine
    -0.72
    ॐ
    -0.72
     feeder
    -0.71
    POSITIVE LOGITS
     Danube
    1.41
     Hungary
    1.18
     Hungarian
    0.94
     Donau
    0.86
     Budapest
    0.85
     Bratislava
    0.82
     Novi
    0.81
     Buda
    0.81
     вен
    0.79
     '?'
    0.79
    Activations Density 0.053%

    No Known Activations