© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59168
    Prev
    Next
    INDEX
    Explanations

    places and their regions

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

    The neuron is strongly activated by standalone numeric tokens (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
     пище
    -0.79
     really
    -0.78
    zzleHttp
    -0.77
     Portland
    -0.75
     &=
    -0.72
     тут
    -0.69
     Tucson
    -0.69
     Balo
    -0.69
    Portland
    -0.68
    ⊖
    -0.68
    POSITIVE LOGITS
     Semarang
    0.97
     台中
    0.94
     Middlesex
    0.83
     Marys
    0.82
     Shropshire
    0.82
     Coimbra
    0.81
     Stillwater
    0.81
    ços
    0.80
    عت
    0.79
     Worcester
    0.79
    Activations Density 0.088%

    No Known Activations