© 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. 22-GEMMASCOPE-RES-131K
    7. 93174
    Prev
    Next
    INDEX
    Explanations

    mission critical

    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_22/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
    おわりに
    -1.66
    来週
    -1.58
    ＊＊＊＊
    -1.55
    定価
    -1.52
    喼
    -1.48
    のではないでしょうか
    -1.45
    今月
    -1.45
    明日は
    -1.45
    もうすぐ
    -1.41
    Much
    -1.41
    POSITIVE LOGITS
    '
    1.75
    ]
    1.52
    ’
    1.52
    .
    1.48
    捗
    1.38
    _
    1.32
    %
    1.31
    ,
    1.28
    物は
    1.27
    )
    1.27
    Activations Density 0.003%

    No Known Activations