© 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. 85045
    Prev
    Next
    INDEX
    Explanations

    Surname or citation fragments

    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
     zimowa
    -1.88
     célè
    -1.85
     męska
    -1.84
     tatuajes
    -1.83
     schoenen
    -1.80
    奩
    -1.73
     evenement
    -1.73
    っちゃう
    -1.73
     rafra
    -1.70
     pourront
    -1.68
    POSITIVE LOGITS
     on
    2.34
     also
    2.31
    </em>
    2.17
     about
    2.03
    </sup>
    1.96
    ↵
    1.91
    毫米
    1.70
    もいい
    1.63
    This
    1.63
     until
    1.62
    Activations Density 0.051%

    No Known Activations