© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104955
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers ending in rd

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

    The neuron detects ordinal-number tokens (e.g. “3rd”)—i.e. numbers with the “rd” suffix.

    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
    </em>
    -2.44
     blah
    -2.42
    rpura
    -2.28
    ⩴
    -2.28
    𝄆
    -2.20
    了一个
    -2.17
    感じです
    -2.17
    </h4>
    -2.17
     immort
    -2.09
     丝
    -2.08
    POSITIVE LOGITS
    rd
    2.94
    uſe
    2.61
     lettore
    2.55
    휀
    2.53
     blz
    2.50
     orologio
    2.48
    .^
    2.45
    是什么
    2.42
    .”
    2.42
     gouvernements
    2.36
    Activations Density 0.005%

    No Known Activations