© 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. 129026
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (digits and number-related punctuation) in the text.

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

    lists of items

    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
    除非
    -1.10
     ché
    -1.03
     了
    -1.02
    reportWebVitals
    -1.00
    geted
    -1.00
     voire
    -1.00
     Descripción
    -0.98
    worldwide
    -0.97
    OrWhiteSpace
    -0.97
    [
    -0.97
    POSITIVE LOGITS
    معرفی
    1.16
     other
    1.16
    Terima
    1.13
    图片来源
    1.11
     others
    1.03
     and
    1.03
    Jawab
    1.02
    していますが
    1.02
    Suka
    1.00
    Postup
    0.99
    Activations Density 0.149%

    No Known Activations