© 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. 66829
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers with months

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

    The neuron detects ordinal-number suffix tokens (e.g. “st,” “nd,” “rd,” “th”) as used in dates.

    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
     लेकिन
    -1.70
     three
    -1.67
     litoral
    -1.65
     two
    -1.61
     five
    -1.57
    棪
    -1.56
    ついでに
    -1.55
     eight
    -1.52
    ～♪
    -1.52
     mutta
    -1.52
    POSITIVE LOGITS
    }
    1.94
     VERY
    1.84
     decidedly
    1.82
     continually
    1.81
     This
    1.80
     unbelievably
    1.79
     principalmente
    1.77
     overly
    1.72
     ridiculously
    1.72
     apenas
    1.70
    Activations Density 0.016%

    No Known Activations