© 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. 42612
    Prev
    Next
    INDEX
    Explanations

    not data or math

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

    The neuron activates on occurrences of “NaN” (or its variants) indicating missing or non-numeric data values.

    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
    
    -2.81
    猡
    -2.47
    
    -2.27
    ättä
    -2.20
    
    -2.19
    ⎔
    -2.16
    轳
    -2.14
    
    -2.11
    垕
    -2.11
    škoda
    -2.08
    POSITIVE LOGITS
    With
    2.89
    {
    2.88
    To
    2.83
    "
    2.81
    e
    2.78
    All
    2.72
    [
    2.69
    2
    2.63
    In
    2.61
    Since
    2.61
    Activations Density 0.003%

    No Known Activations