© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66422
    Prev
    Next
    INDEX
    Explanations

    end dates for events

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

    The neuron detects tokens that form dates and time spans (e.g., months, days, “through,” numerals) in event scheduling contexts.

    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
     that
    -1.64
     instances
    -1.17
     when
    -1.16
     U
    -1.12
     tools
    -1.11
     whose
    -1.08
     where
    -1.07
     data
    -1.06
    that
    -1.03
     things
    -1.02
    POSITIVE LOGITS
    until
    1.30
     until
    1.24
    浑身
    1.18
    meture
    1.15
     fotográfica
    1.12
    Geograf
    1.12
    ᾖ
    1.10
    Namen
    1.09
     erbjud
    1.09
    ról
    1.08
    Activations Density 0.017%

    No Known Activations