© 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. 20351
    Prev
    Next
    INDEX
    Explanations

    Raptor, Viper, Mitsubishi, Chrys

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

    The neuron is strongly triggered by capitalized proper names—especially brand, model, or project names (e.g. “Raptor,” “Evolette,” “Mitsubishi,” “Outlander”).

    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
    <strong>
    -3.11
    io
    -2.94
    out
    -2.75
    ۔
    -2.66
    B
    -2.66
    on
    -2.66
    as
    -2.64
    ۵
    -2.63
    </h3>
    -2.61
    the
    -2.61
    POSITIVE LOGITS
     欣赏
    3.00
     哪些
    2.48
    
    2.38
     extranjera
    2.30
     ทำ
    2.30
     ….
    2.19
     the
    2.13
    她和
    2.13
    푢
    2.11
     为什么
    2.09
    Activations Density 0.004%

    No Known Activations