© 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. 19447
    Prev
    Next
    INDEX
    Explanations

    cmath, NES, Ну, Daredevil

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

    The neuron fires on occurrences of the character sequence “nu” (in any case).

    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
    
    -2.83
    絰
    -2.78
    薷
    -2.73
     帅气
    -2.70
    甦
    -2.58
    鉭
    -2.58
    like
    -2.55
    辂
    -2.45
    lgari
    -2.36
     Если
    -2.33
    POSITIVE LOGITS
     {
    3.06
     includes
    2.86
     (&
    2.77
     haciendo
    2.77
     *
    2.75
    l
    2.75
     kedua
    2.73
    a
    2.72
     :
    2.69
     was
    2.67
    Activations Density 0.005%

    No Known Activations