© 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. 22-GEMMASCOPE-RES-131K
    7. 36035
    Prev
    Next
    INDEX
    Explanations

    describing normalcy

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

    The neuron is triggered by instances of the word “normal.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ompok
    -0.98
     distinción
    -0.95
    FONTE
    -0.91
    -/
    -0.89
    ッグ
    -0.88
     vedno
    -0.88
    コスパ
    -0.83
    ització
    -0.82
    ческая
    -0.82
    adrez
    -0.82
    POSITIVE LOGITS
     normal
    1.95
     normalen
    1.66
    normal
    1.59
    正常
    1.50
     normale
    1.39
    Normal
    1.38
    NORMAL
    1.32
     NORMAL
    1.24
     ordinary
    1.22
     silvestre
    1.21
    Activations Density 0.105%

    No Known Activations