© 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. 117003
    Prev
    Next
    INDEX
    Explanations

    Webster and Spade names

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

    The neuron strongly activates on instances of the name “Webster.”

    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
    Dichloroprop
    -0.80
     productive
    -0.79
     Sherlock
    -0.79
    ummy
    -0.77
     Eti
    -0.77
    klus
    -0.74
     maleta
    -0.73
    钣
    -0.72
     φί
    -0.72
     almohada
    -0.72
    POSITIVE LOGITS
     Groves
    0.93
    suje
    0.77
    RIO
    0.71
    
    0.68
     vår
    0.68
     Defines
    0.68
     Inspect
    0.68
    defining
    0.67
     vairāk
    0.67
     Defining
    0.66
    Activations Density 0.014%

    No Known Activations