© 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. 47588
    Prev
    Next
    INDEX
    Explanations

    rules and regulations

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

    The neuron fires on sequences of digits (and their surrounding spaces) used as numeric identifiers (e.g. rule numbers, section numbers, headings) 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_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
    \\
    -2.36
     «
    -2.30
     («
    -2.00
     в
    -1.92
    ’
    -1.90
    ',
    -1.85
    \
    -1.84
    ),
    -1.84
    ?
    -1.84
    ↵↵
    -1.81
    POSITIVE LOGITS
     grátis
    2.11
     also
    2.11
    啻
    2.08
     oferecer
    2.05
     terceiros
    2.02
     folosi
    1.99
    睺
    1.99
    塤
    1.97
     incluem
    1.96
     Años
    1.95
    Activations Density 0.023%

    No Known Activations