© 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. 34-GEMMASCOPE-RES-131K
    4. 50406
    Prev
    Next
    INDEX
    Explanations

    typedef struct

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

    The neuron is picking out numeric tokens (integer literals and other numbers) in code.

    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
     tủ
    -0.77
    箋
    -0.77
    rettet
    -0.77
    おう
    -0.73
    bertas
    -0.72
     panties
    -0.72
    ^-
    -0.72
     Canaria
    -0.70
     exponer
    -0.68
     lungs
    -0.67
    POSITIVE LOGITS
     struct
    5.13
    struct
    4.94
     structural
    2.91
     structure
    2.70
    结构
    2.69
     Struct
    2.67
    Struct
    2.48
     structs
    2.45
    STRUCT
    2.41
    Structural
    2.34
    Activations Density 0.149%

    No Known Activations