© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29892
    Prev
    Next
    INDEX
    Explanations

    combinations and permutations

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

    The neuron strongly activates on numeric tokens, mathematical operators, and formula‐like expressions—essentially spotting math notation and number‐heavy problem statements.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     悠
    -0.75
     menghub
    -0.73
    jíma
    -0.72
    トレ
    -0.70
    嫁
    -0.69
    вока
    -0.69
    ++];
    -0.68
    četně
    -0.68
    сторія
    -0.67
    蒟
    -0.65
    POSITIVE LOGITS
     combinations
    1.93
     combination
    1.70
     permutations
    1.63
    choose
    1.62
     permutation
    1.61
     Combinations
    1.60
     Combination
    1.59
    combination
    1.57
    comb
    1.56
     choose
    1.55
    Activations Density 0.093%

    No Known Activations