© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14087
    Prev
    Next
    INDEX
    Explanations

    asserting non-null values

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

    The neuron fires on null‐safety annotations (e.g. @NonNull, @NotNull) 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_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
     другими
    -2.02
     sogenannten
    -1.91
     späteren
    -1.87
     perils
    -1.83
     {
    -1.83
     impoverished
    -1.80
     bustling
    -1.79
    たまた
    -1.77
     arduous
    -1.76
     zahlreichen
    -1.74
    POSITIVE LOGITS
     untuk
    2.13
    ਂ
    2.05
    UserDefaults
    2.05
    >
    1.98
    н
    1.97
    mente
    1.95
     februari
    1.93
    ']>
    1.93
    ：[
    1.92
     abz
    1.92
    Activations Density 0.001%

    No Known Activations