© 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. 10-GEMMASCOPE-RES-131K
    7. 90617
    Prev
    Next
    INDEX
    Explanations

    code comments and programming constructs

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

    The neuron fires strongly on printf/scanf format‐string tokens (e.g. the “\” that opens a string literal and the “%d”/“%d%d”/“%d%d%d” specifiers), i.e. it detects C I/O format specifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     its
    -1.84
    r
    -1.54
     itself
    -1.46
     But
    -1.45
     Its
    -1.44
    -1.42
    x
    -1.40
     be
    -1.40
     s
    -1.38
    s
    -1.36
    POSITIVE LOGITS
    ໊
    1.91
     świecie
    1.72
    犼
    1.68
    虓
    1.66
     całym
    1.66
    苳
    1.65
    嫱
    1.63
    
    1.63
    荭
    1.62
     炖
    1.59
    Activations Density 0.001%
    No Known Activations