© 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. 69244
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and anniversaries

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

    The neuron detects ordinal-number suffixes—specifically the “th” token following a numeral (e.g., in dates or anniversaries).

    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
     porsi
    -2.17
     zobac
    -2.17
     How
    -2.08
     miljoen
    -2.03
     When
    -2.00
     emosi
    -1.96
    ");
    -1.91
     To
    -1.88
     počas
    -1.88
    
    -1.88
    POSITIVE LOGITS
    0
    3.36
    </strong>
    2.30
    не
    2.17
    </em>
    2.13
    支払い
    1.91
    さんは
    1.89
     cinque
    1.86
    ру
    1.84
     ï
    1.84
     tragically
    1.82
    Activations Density 0.025%

    No Known Activations