© 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. 34-GEMMASCOPE-RES-131K
    7. 92202
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

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

    The neuron responds to numeric tokens that denote tournament structure and results—round numbers, seed or draw positions, and match‐score figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     whose
    -1.18
     from
    -1.06
     over
    -1.06
     five
    -1.05
     all
    -1.03
     both
    -1.03
     really
    -1.01
     some
    -0.99
     what
    -0.99
     at
    -0.97
    POSITIVE LOGITS
     TLV
    0.88
     olmad
    0.88
     différentes
    0.88
     Craigslist
    0.87
     выигра
    0.86
     Absent
    0.86
     maven
    0.86
     diverses
    0.84
    ंगे
    0.84
     partici
    0.84
    Activations Density 0.009%

    No Known Activations