© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19262
    Prev
    Next
    INDEX
    Explanations

    Washington and New York places

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

    The neuron detects mentions of the place name “Washington.”

    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
    _
    -1.57
    >
    -1.38
    ]
    -1.35
     \
    -1.34
     –
    -1.30
     barcel
    -1.27
    I
    -1.26
    .,
    -1.24
    P
    -1.24
    -
    -1.23
    POSITIVE LOGITS
     drugi
    1.48
     sposob
    1.30
     energii
    1.29
     ozdob
    1.29
    ریب
    1.27
     klubu
    1.27
     hrab
    1.24
    fordern
    1.23
     stanu
    1.23
    nicht
    1.21
    Activations Density 0.067%

    No Known Activations