© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65791
    Prev
    Next
    INDEX
    Explanations

    times and periods

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

    The neuron identifies temporal‐reference phrases that locate events in time (e.g. “around the time of…” or “this time of year”).

    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
    Friday
    -1.42
    aldehyde
    -1.35
    直至
    -1.34
     distintos
    -1.32
    哙
    -1.30
    acce
    -1.27
     encontrar
    -1.26
     jusqu
    -1.25
    Wednesday
    -1.23
    ENES
    -1.23
    POSITIVE LOGITS
     decoradas
    1.40
    ilares
    1.37
    留意
    1.36
    ührung
    1.35
    ginine
    1.34
    »,
    1.31
    urunan
    1.31
     increased
    1.31
     hendak
    1.30
    gunaan
    1.29
    Activations Density 0.022%

    No Known Activations