© 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. 34956
    Prev
    Next
    INDEX
    Explanations

    class method names

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

    The neuron is firing on long runs of leading whitespace (i.e. indented code lines).

    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
    Föld
    -1.63
     hunde
    -1.48
    Какво
    -1.45
    肮
    -1.44
    こともあり
    -1.44
    Материал
    -1.44
    꽁
    -1.41
    Ако
    -1.38
    érable
    -1.36
     keramik
    -1.36
    POSITIVE LOGITS
    //
    2.39
    /**
    1.80
    *
    1.78
    #
    1.58
    なので
    1.54
    @
    1.52
    ↵↵↵↵
    1.50
    /*
    1.46
    {
    1.46
    ↵↵
    1.44
    Activations Density 0.009%

    No Known Activations