© 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. 8996
    Prev
    Next
    INDEX
    Explanations

    switzerland, canton, municipality, federal, suicide, bank

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

    The neuron detects mentions of Switzerland or Swiss places and administrative units.

    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
    комплект
    -1.04
    ➭
    -0.94
    ändig
    -0.94
     underserved
    -0.91
     чёрный
    -0.90
     dreamstime
    -0.90
    –¿
    -0.90
    IRD
    -0.90
     ممکن
    -0.89
    ladelphia
    -0.88
    POSITIVE LOGITS
     truco
    1.27
     tornillo
    1.26
     esqueleto
    1.18
     there
    1.14
     embrague
    1.14
     sitios
    1.13
    när
    1.10
     hábit
    1.09
     trámite
    1.09
     reservar
    1.08
    Activations Density 0.144%

    No Known Activations