© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71832
    Prev
    Next
    INDEX
    Explanations

    names ending in ole, upe, ide, ola

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

    Nigerian names or words that appear to be names from Nigerian languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     queridos
    -2.05
     สำหรับ
    -1.86
     obstruct
    -1.85
    驀
    -1.80
     škoda
    -1.80
     znám
    -1.80
    風格
    -1.80
    是吗
    -1.79
    ⵎ
    -1.77
     nuestra
    -1.74
    POSITIVE LOGITS
    ”
    2.50
    7
    2.05
    </em>
    2.03
    4
    1.94
     to
    1.90
    2
    1.86
    8
    1.85
    не
    1.82
    <em>
    1.82
    ()
    1.76
    Activations Density 0.008%

    No Known Activations