© 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. 66145
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions

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

    The neuron fires on numeric literals (digit sequences) 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_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
    ！！！！！
    -1.17
     Meksiko
    -1.09
    でございます
    -1.08
     Desember
    -1.07
     katk
    -1.01
    察觉
    -1.00
     Тран
    -0.98
    atürk
    -0.97
     endast
    -0.96
     viewDidLoad
    -0.94
    POSITIVE LOGITS
     other
    1.25
     Krzysz
    1.14
     others
    1.13
     its
    1.03
     rapporto
    1.03
     marito
    1.02
    広く
    1.02
    viale
    1.02
     gelesen
    0.99
    .《
    0.99
    Activations Density 0.095%

    No Known Activations