© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60678
    Prev
    Next
    INDEX
    Explanations

    global or world related topics discussions

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

    The neuron fires on references to broad, planetary‐ or worldwide‐scale contexts (e.g. “global,” “world,” “planet”).

    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
    mentaires
    -1.62
     setidaknya
    -1.56
    ricts
    -1.49
     Février
    -1.48
     kertas
    -1.48
     situações
    -1.44
     daardoor
    -1.44
    ємо
    -1.44
    ệu
    -1.43
     diğer
    -1.42
    POSITIVE LOGITS
    /
    1.70
    :
    1.65
     
    1.59
    <blockquote>
    1.46
    u
    1.39
     équipement
    1.35
    ble
    1.34
    ti
    1.32
     any
    1.29
     replete
    1.28
    Activations Density 0.044%

    No Known Activations