© 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. 22-GEMMASCOPE-RES-131K
    7. 73042
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    This neuron activates on date expressions (month names, days, and years).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     only
    -1.48
     which
    -1.41
     with
    -1.41
     just
    -1.34
     because
    -1.31
     all
    -1.30
     by
    -1.27
     what
    -1.27
     their
    -1.26
     using
    -1.26
    POSITIVE LOGITS
     💕
    1.22
    ⚌
    1.16
     ___________
    1.15
     REALLY
    1.11
    ,;
    1.10
     tranquil
    1.09
     ____________
    1.09
    Schicken
    1.08
    λών
    1.08
    Télécharger
    1.07
    Activations Density 0.002%

    No Known Activations