© 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. 83990
    Prev
    Next
    INDEX
    Explanations

    National Highway numbers

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

    This neuron activates on numeric tokens and measurements (e.g., highway numbers, distances, years), i.e. any numeric information 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
    Nome
    -0.85
    罗斯
    -0.75
    Nguồn
    -0.74
    seq
    -0.72
    ご注文
    -0.71
    NOME
    -0.71
     газе
    -0.70
    アメリカ
    -0.70
    注射
    -0.69
    érant
    -0.69
    POSITIVE LOGITS
     NH
    2.28
     National
    1.99
     national
    1.91
    NH
    1.84
    National
    1.73
    national
    1.64
    NATIONAL
    1.46
     NATIONAL
    1.44
     nationale
    1.33
     Национа
    1.25
    Activations Density 0.023%

    No Known Activations