© 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. 85186
    Prev
    Next
    INDEX
    Explanations

    names in different languages

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

    The neuron fires on the Spanish heading “Nombre,” i.e. instances of the label “Name.”

    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
    鼉
    -2.81
     famosos
    -2.73
     společnosti
    -2.70
    はどう
    -2.67
     ottimo
    -2.64
     maravill
    -2.55
     payé
    -2.55
     "
    -2.53
    埽
    -2.48
    hidup
    -2.42
    POSITIVE LOGITS
    .“
    3.38
    趼
    3.05
    灕
    2.80
    龊
    2.61
    x
    2.50
     agrico
    2.41
     begle
    2.36
     gewähr
    2.34
    姈
    2.34
    醂
    2.22
    Activations Density 0.001%

    No Known Activations