© 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. 22-GEMMASCOPE-RES-131K
    7. 32710
    Prev
    Next
    INDEX
    Explanations

    lakhs and k amounts

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

    The neuron activates on large‐scale numeric unit markers—e.g. “k,” “lakh,” “lakhs,” and “crore.”

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ῎
    -1.83
    ’)
    -1.68
     tady
    -1.66
     certain
    -1.61
    屃
    -1.60
    䊉
    -1.59
    
    -1.59
    の時に
    -1.58
    ’).
    -1.52
     to
    -1.51
    POSITIVE LOGITS
    Their
    2.16
    Because
    1.95
    Being
    1.87
    Obviously
    1.84
    Those
    1.80
    Shortly
    1.80
    Initially
    1.75
    Its
    1.75
    During
    1.73
    Regardless
    1.72
    Activations Density 0.009%

    No Known Activations