© 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. 13152
    Prev
    Next
    INDEX
    Explanations

    set, cstring, setup

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

    The neuron fires strongly on mentions of memory‐related operations and headers (e.g. “memset”, “MEMSET”, `<memory>`, `<cstring>`).

    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
     climático
    -1.25
     "
    -1.23
    [
    -1.22
    ).
    -1.21
    ,(
    -1.20
    Of
    -1.19
    keda
    -1.17
     essas
    -1.16
    みそ
    -1.15
    ,"
    -1.13
    POSITIVE LOGITS
     zina
    1.22
     perdon
    1.21
    月は
    1.20
    
    1.18
    金牛
    1.18
     født
    1.17
     mignon
    1.16
    dition
    1.16
     seco
    1.16
    ARANCE
    1.16
    Activations Density 0.001%

    No Known Activations