© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70009
    Prev
    Next
    INDEX
    Explanations

    Comme une, effervescent, Hyperolius

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

    French words, particularly the word "Comme" (meaning "like" or "as").

    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
     con
    -3.11
     {
    -2.89
    {
    -2.61
     dengan
    -2.56
    翆
    -2.22
    さらに
    -2.14
     como
    -2.08
     avec
    -2.02
    ſelves
    -2.00
    确保
    -1.97
    POSITIVE LOGITS
     ragaz
    2.55
    笮
    2.50
    咐
    2.48
    欵
    2.48
    齜
    2.48
    灕
    2.44
    涐
    2.41
    墬
    2.39
     gire
    2.38
     kwamba
    2.36
    Activations Density 0.000%

    No Known Activations