© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8622
    Prev
    Next
    INDEX
    Explanations

    Vietnamese names or smiley faces

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

    The neuron tends to fire on low‐frequency or otherwise “uncommon” tokens (e.g. rare names like “Nguyen,” the Greek math symbol “sigma,” or emoticon “; )”).

    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
    e
    -3.78
    as
    -3.63
    ing
    -3.53
    At
    -3.11
    In
    -3.03
    on
    -2.92
    g
    -2.88
    Y
    -2.88
    h
    -2.81
    [
    -2.73
    POSITIVE LOGITS
    嫑
    3.36
     cadeiras
    3.16
    
    3.00
    妧
    2.95
     estadía
    2.75
    genodigd
    2.64
     houſe
    2.61
     estrelas
    2.58
     但
    2.58
    蚍
    2.56
    Activations Density 0.004%

    No Known Activations