© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58544
    Prev
    Next
    INDEX
    Explanations

    ordinal suffixes in dates

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

    The neuron activates on the “th” suffix in ordinal date tokens (e.g. the “th” in “11th,” “29th,” “4th,” 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_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
     sufficient
    -1.20
     was
    -1.07
     even
    -1.01
    }
    -0.99
    ặn
    -0.97
    𓈒
    -0.97
     constructed
    -0.94
     that
    -0.93
     solely
    -0.90
    masin
    -0.90
    POSITIVE LOGITS
    these
    1.04
    Could
    1.02
    Visitors
    1.00
    这里是
    0.98
    عرِّف
    0.98
     graders
    0.98
    壺
    0.96
    Which
    0.96
    (?)
    0.95
     douleurs
    0.95
    Activations Density 0.006%

    No Known Activations