© 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. 79092
    Prev
    Next
    INDEX
    Explanations

    ordinal time periods

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

    The neuron selectively activates on ordinal time expressions (e.g. “first,” “second,” “last”) that locate events in a sequence or calendar.

    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
    ()?;
    -0.81
     つの
    -0.81
    歺
    -0.80
     certaines
    -0.79
     ніж
    -0.79
    whelming
    -0.78
    Более
    -0.78
    ately
    -0.77
    certain
    -0.75
    imą
    -0.75
    POSITIVE LOGITS
     week
    2.09
     weeks
    1.27
     weekend
    1.18
    week
    1.12
     part
    1.10
     Week
    1.02
    WEEK
    0.97
     full
    0.97
     days
    0.94
     неделю
    0.93
    Activations Density 0.029%

    No Known Activations