© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43782
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and descriptive words

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

    The neuron detects the “th” suffix used to mark ordinal numbers (e.g. in “4th,” “7th,” “14th,” etc.).

    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
     perú
    -1.85
     AFRICAN
    -1.84
     prêts
    -1.77
     แปล
    -1.75
    quần
    -1.74
    獁
    -1.72
    adakan
    -1.66
    给他们
    -1.64
    
    -1.63
    ícone
    -1.61
    POSITIVE LOGITS
     in
    2.50
     the
    2.36
    s
    2.27
    '
    2.05
    c
    1.95
    n
    1.88
     those
    1.86
    An
    1.84
     each
    1.77
    m
    1.76
    Activations Density 0.033%

    No Known Activations