© 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. 90884
    Prev
    Next
    INDEX
    Explanations

    Ethiopia, Seattle

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

    The neuron is picking up on proper names and place names (i.e. named entities).

    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
    嫆
    -1.89
    婼
    -1.78
    ᥫ
    -1.73
    
    -1.73
    providedIn
    -1.66
    熜
    -1.66
    ྄
    -1.64
    âncias
    -1.63
    越来越多
    -1.62
     manifests
    -1.61
    POSITIVE LOGITS
     also
    1.86
     who
    1.65
    ↵
    1.43
    ，
    1.41
    ͎
    1.41
     actually
    1.39
    ('
    1.38
     (
    1.38
    (
    1.37
    ['
    1.36
    Activations Density 0.005%

    No Known Activations