© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 558
    Prev
    Next
    INDEX
    Explanations

    United States Constitution

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

    The neuron fires on numeric tokens (numbers, dates, or other 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
    REWRITE
    -1.09
     in
    -1.03
    忖
    -1.00
     ,
    -0.99
     can
    -0.96
     лимон
    -0.96
     opener
    -0.93
     https
    -0.93
    красный
    -0.93
     varias
    -0.93
    POSITIVE LOGITS
    ">&
    1.23
    FWIW
    1.13
    歟
    1.12
    Advertisements
    1.11
    WordPress
    1.11
     pertanto
    1.09
    Reminds
    1.09
     elek
    1.08
     hek
    1.05
     webbplats
    1.05
    Activations Density 0.052%

    No Known Activations