© 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. 66473
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
     even
    -1.05
    </h5>
    -0.99
    Stalin
    -0.96
     дори
    -0.96
     incluso
    -0.94
    гий
    -0.93
    abes
    -0.93
     автомобилей
    -0.93
    不得
    -0.93
    ("/:
    -0.92
    POSITIVE LOGITS
    Producción
    1.13
     weihnachten
    1.09
     Sortiment
    1.09
     gerai
    1.09
    研究生
    1.06
     kurie
    1.05
    Hlav
    1.05
    Çok
    1.02
    招生
    1.02
    してみると
    1.02
    Activations Density 0.012%

    No Known Activations