© 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. 42118
    Prev
    Next
    INDEX
    Explanations

    lieu, milieu, Elixir, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    the
    -3.80
    ?
    -3.67
    轫
    -3.03
    d
    -2.98
    ↵↵
    -2.84
    汭
    -2.84
    擻
    -2.81
    a
    -2.72
    क्टर
    -2.66
    Ꭳ
    -2.64
    POSITIVE LOGITS
     ของ
    3.14
    蹰
    2.78
     Of
    2.75
     But
    2.63
     voleva
    2.56
    跟
    2.56
    ?"
    2.55
    籥
    2.55
     kimdir
    2.53
    ！"
    2.52
    Activations Density 0.005%

    No Known Activations