© 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. 64515
    Prev
    Next
    INDEX
    Explanations

    Leeds and Yorkshire locations

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

    The neuron is looking for numeric tokens or sequences of digits (i.e. numbers) 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
     نیک
    -0.79
     شیراز
    -0.74
    phot
    -0.74
    purl
    -0.69
    upan
    -0.69
    🚾
    -0.68
    reachable
    -0.68
     uhr
    -0.68
    organization
    -0.67
    licence
    -0.67
    POSITIVE LOGITS
     Leeds
    1.87
    Leeds
    1.73
     Whites
    1.30
     Yorkshire
    1.17
     Marcelo
    1.15
    Marcelo
    1.10
    Yorkshire
    1.03
    Whites
    0.94
     Biel
    0.83
     Ahmedabad
    0.82
    Activations Density 0.032%

    No Known Activations