© 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. 22-GEMMASCOPE-RES-131K
    7. 75008
    Prev
    Next
    INDEX
    Explanations

    localization and technical terms

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

    This neuron fires on chunks of text belonging to Portuguese localization strings (i.e. parts of translated Portuguese words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     
    -1.16
     mé
    -1.10
     positif
    -1.07
     bú
    -1.06
    camis
    -1.06
     rése
    -1.03
     sés
    -1.02
     évé
    -1.02
    paru
    -1.00
     (
    -0.99
    POSITIVE LOGITS
     WQS
    1.23
     Auffassung
    1.21
     Sejarah
    1.19
     ''
    1.16
     國際
    1.15
    💒
    1.11
     '--
    1.10
     MAV
    1.09
     pediat
    1.09
     Unterscheidung
    1.09
    Activations Density 0.001%

    No Known Activations