© 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. 104553
    Prev
    Next
    INDEX
    Explanations

    digits followed by alpha or punctuation

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

    numerical reference labels in patent documents that refer to components or parts in technical diagrams.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects standalone numerals used as reference or enumeration labels (e.g. section numbers, figure/item callouts) in technical documents.

    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
     because
    -2.52
     if
    -2.45
     for
    -2.33
     after
    -2.09
     as
    -2.09
     in
    -1.90
     also
    -1.90
     there
    -1.88
     Also
    -1.83
     and
    -1.82
    POSITIVE LOGITS
     maniere
    1.88
    𓁹
    1.84
    iring
    1.70
    obut
    1.67
    崀
    1.66
     créer
    1.62
    蟊
    1.62
     zoude
    1.60
     horloge
    1.59
    
    1.59
    Activations Density 0.025%

    No Known Activations