© 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. 34-GEMMASCOPE-RES-131K
    4. 87064
    Prev
    Next
    INDEX
    Explanations

    names from foreign languages

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

    The neuron detects the phrase “is from” used to introduce an origin or etymology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ᆫ
    -0.91
    Detalles
    -0.87
    grano
    -0.84
     imprim
    -0.83
     способствует
    -0.83
    loride
    -0.81
    Pilih
    -0.81
     taxa
    -0.81
    ኢ
    -0.80
    něž
    -0.79
    POSITIVE LOGITS
     Greek
    1.90
     Arabic
    1.52
     French
    1.50
     Spanish
    1.49
     Hebrew
    1.48
     Italian
    1.45
     German
    1.30
     Sanskrit
    1.29
     Portuguese
    1.20
    Greek
    1.16
    Activations Density 0.056%

    No Known Activations