© 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. 34-GEMMASCOPE-RES-131K
    7. 90144
    Prev
    Next
    INDEX
    Explanations

    declarations with !, ?

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

    This neuron fires on programming‐language identifiers, especially class/type names in code (e.g. UIView subclasses, database reference types, etc.).

    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
     especially
    -1.28
     particularly
    -1.15
     as
    -0.95
     why
    -0.94
     their
    -0.93
     latter
    -0.86
     such
    -0.84
     particular
    -0.83
     soprattutto
    -0.82
    ➼
    -0.80
    POSITIVE LOGITS
     {
    1.03
    !}
    0.88
     würd
    0.87
    KAB
    0.82
    ǂ
    0.81
    !
    0.80
     \{
    0.79
    Neill
    0.79
     $\{
    0.78
    šin
    0.78
    Activations Density 0.006%

    No Known Activations