© 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. 22-GEMMASCOPE-RES-131K
    4. 39680
    Prev
    Next
    INDEX
    Explanations

    times, but, then, occasion

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

    The neuron is primarily detecting the Chinese temporal marker “时,” which introduces time/“when” clauses.

    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
     for
    -1.76
     and
    -1.53
     until
    -1.50
     while
    -1.47
    }$
    -1.45
    <<<<<<<
    -1.41
     prior
    -1.38
     of
    -1.35
     &&
    
    -1.35
    T
    -1.31
    POSITIVE LOGITS
    ,
    1.90
    6
    1.61
    ،
    1.60
     trám
    1.59
    these
    1.48
     czeko
    1.43
    labili
    1.42
    However
    1.41
     invertir
    1.40
     kokos
    1.38
    Activations Density 0.003%

    No Known Activations