© 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. 40207
    Prev
    Next
    INDEX
    Explanations

    enumerated lists and identifiers

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

    This neuron detects numeric data entries (e.g., measurements, coordinates, figure/table indices, and other numbers) embedded 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
     to
    -1.83
     with
    -1.66
     by
    -1.27
     in
    -1.25
     on
    -1.18
     from
    -1.10
     (
    -1.05
     When
    -1.02
     at
    -0.99
    onPause
    -0.94
    POSITIVE LOGITS
     cinza
    1.12
    נשים
    1.06
     diversos
    1.06
    푉
    1.05
    还能
    1.05
     nasz
    1.05
     verdadeira
    1.04
     ganhou
    1.04
    ఌ
    1.04
     많은
    1.03
    Activations Density 0.019%

    No Known Activations