© 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. 10-GEMMASCOPE-RES-131K
    7. 61114
    Prev
    Next
    INDEX
    Explanations

    article number

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

    The neuron fires on numbered legal or statutory article references (e.g. “Article 85,” “Art. 2,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -2.20
    ",
    -1.70
    ff
    -1.61
    fl
    -1.59
     was
    -1.59
    ?
    -1.59
    </h2>
    -1.52
     její
    -1.50
    with
    -1.45
    tiously
    -1.45
    POSITIVE LOGITS
     of
    2.31
     both
    1.67
     about
    1.67
    even
    1.66
    Menurut
    1.65
     Although
    1.60
    に来
    1.54
    Etimología
    1.52
     it
    1.52
     reason
    1.52
    Activations Density 0.006%

    No Known Activations