© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128829
    Prev
    Next
    INDEX
    Explanations

    The neuron fires whenever it encounters standalone numeric literals (i.e. sequences of digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    團隊
    -0.79
     toppen
    -0.79
     hipote
    -0.78
     arkiv
    -0.78
    стка
    -0.75
    brada
    -0.74
     kriminal
    -0.73
     във
    -0.73
     optik
    -0.73
    écial
    -0.71
    POSITIVE LOGITS
     Preisen
    0.83
    Демографія
    0.82
     estructuras
    0.80
     Province
    0.77
    nič
    0.77
     SINGH
    0.77
    şme
    0.76
     troupes
    0.76
    вер
    0.76
     Punjabi
    0.75
    Activations Density 0.065%

    No Known Activations