© 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. 792
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     actually
    -2.34
     so
    -2.23
     could
    -2.06
     really
    -2.03
     also
    -2.00
     had
    -2.00
     alltså
    -1.96
     truly
    -1.91
    </i>
    -1.90
     only
    -1.90
    POSITIVE LOGITS
     the
    2.89
    𐄁
    1.94
    转头
    1.94
    当然是
    1.92
     devuelve
    1.92
     diverses
    1.91
    0
    1.91
     différents
    1.90
    帔
    1.88
     evangé
    1.85
    Activations Density 0.223%

    No Known Activations