© 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. 19279
    Prev
    Next
    INDEX
    Explanations

    errors and mistakes

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

    This neuron detects non-English text snippets, especially Spanish- or Portuguese-language fragments.

    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
    And
    -2.11
    Its
    -1.66
     никаких
    -1.61
     ganze
    -1.54
    Of
    -1.53
     tiefe
    -1.52
    ISBN
    -1.45
     nella
    -1.41
    In
    -1.41
    erapeutics
    -1.40
    POSITIVE LOGITS
    ături
    1.68
    逦
    1.67
    女
    1.62
     シングル
    1.46
    prender
    1.42
    蚡
    1.42
     contamos
    1.41
     encontrarás
    1.39
     entrée
    1.38
    UDE
    1.33
    Activations Density 0.004%

    No Known Activations