© 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. 21795
    Prev
    Next
    INDEX
    Explanations

    city centre or CBD

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

    This neuron detects mentions of a place’s central area (e.g. the term “centre” as in “city centre”).

    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
    廰
    -1.57
    おわりに
    -1.55
    밟
    -1.55
     vanno
    -1.53
    ного
    -1.53
    !』
    -1.53
    ons
    -1.52
    []);
    -1.52
    にかく
    -1.51
    )
    
    -1.48
    POSITIVE LOGITS
    逦
    1.91
     irrational
    1.72
     arche
    1.70
     façade
    1.63
    魉
    1.63
    릭터
    1.62
    彳
    1.61
    ⅖
    1.59
     opportunistic
    1.59
    哈哈哈
    1.59
    Activations Density 0.002%

    No Known Activations