© 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. 22-GEMMASCOPE-RES-131K
    4. 98280
    Prev
    Next
    INDEX
    Explanations

    Massachusetts and Boston

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

    The neuron is detecting mentions of Massachusetts locations or abbreviations (e.g., Boston, MA, Supreme Judicial Court of Massachusetts).

    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
    </strong>
    -1.52
    
    -1.29
     preferido
    -1.24
    tori
    -1.23
     yayınları
    -1.17
     compuestos
    -1.16
    懼
    -1.16
    ジアム
    -1.15
    $,
    
    -1.15
    ’:
    -1.14
    POSITIVE LOGITS
     Massachusetts
    2.34
    Massachusetts
    2.05
     Boston
    1.88
    Boston
    1.80
    BOSTON
    1.76
     Celtics
    1.38
     BOSTON
    1.34
    1
    1.34
     Mass
    1.30
     MIT
    1.27
    Activations Density 0.080%

    No Known Activations