© 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. 160
    Prev
    Next
    INDEX
    Explanations

    Chernobyl, Indira, MySpace, Flipkart

    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
    コンサート
    -2.23
    ヨーロ
    -2.13
    パートナー
    -2.03
     weird
    -1.87
    libft
    -1.85
    <bos>
    -1.78
     antwortete
    -1.77
     is
    -1.77
    belongsTo
    -1.75
    .”
    -1.73
    POSITIVE LOGITS
    魠
    2.30
     faſt
    2.14
    .
    2.09
     évi
    2.05
     Onze
    2.00
    殽
    2.00
     fueling
    1.99
    every
    1.95
    during
    1.91
     tranſ
    1.89
    Activations Density 0.015%

    No Known Activations