© 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. 10-GEMMASCOPE-RES-131K
    7. 15305
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    The neuron activates on date and time expressions (month names, day/month numbers, timestamps).

    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
     tambien
    -1.71
     and
    -1.66
     também
    -1.63
     "
    -1.58
    Also
    -1.43
     ("
    -1.41
    Questo
    -1.40
     مقالات
    -1.38
    also
    -1.36
    entic
    -1.34
    POSITIVE LOGITS
     their
    2.53
     they
    2.14
    idän
    1.52
     seguras
    1.51
     thier
    1.45
    gucigalpa
    1.42
    </h2>
    1.42
     červen
    1.41
     asciug
    1.38
     new
    1.38
    Activations Density 0.004%

    No Known Activations