© 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. 34-GEMMASCOPE-RES-131K
    7. 66400
    Prev
    Next
    INDEX
    Explanations

    flush, write, close

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

    The neuron fires strongly on numeric literals (i.e. tokens composed of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     uyar
    -0.79
    NSS
    -0.79
    かげ
    -0.78
    readString
    -0.77
    haq
    -0.73
    斎藤
    -0.71
    nss
    -0.70
     auquel
    -0.70
    Alerter
    -0.70
    JsonHelper
    -0.70
    POSITIVE LOGITS
    flush
    0.93
     flush
    0.93
    FLUSH
    0.92
    효
    0.88
     Flush
    0.88
    ())));
    0.83
    规划
    0.83
     write
    0.81
     flushed
    0.81
    이블
    0.80
    Activations Density 0.004%

    No Known Activations