© 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. 39686
    Prev
    Next
    INDEX
    Explanations

    buffer and flush operations

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

    The neuron detects code references to buffering and flush operations.

    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
     kopp
    -1.23
    ations
    -1.15
     Chaque
    -1.13
     hırka
    -1.13
    这样
    -1.11
    wór
    -1.09
     akku
    -1.09
    度は
    -1.09
     kado
    -1.08
    をしました
    -1.07
    POSITIVE LOGITS
    اض
    1.21
     несмотря
    1.20
    rógeno
    1.16
     poivre
    1.09
    TemporalType
    1.09
    多久
    1.05
     erase
    1.03
    שלום
    1.03
     commence
    1.02
    texpr
    1.02
    Activations Density 0.002%

    No Known Activations