© 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. 120007
    Prev
    Next
    INDEX
    Explanations

    way to/of

    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
     faldas
    -2.20
     motocicletas
    -2.13
     enamorado
    -1.93
    jadikan
    -1.93
     camión
    -1.92
     íntimo
    -1.91
     they
    -1.90
     viviendas
    -1.89
     condenado
    -1.88
     estadía
    -1.86
    POSITIVE LOGITS
     Our
    1.95
    </h4>
    1.93
    </u>
    1.89
    /
    1.89
    ”
    1.79
    them
    1.73
    ton
    1.71
    </h5>
    1.71
    v
    1.63
    matitis
    1.60
    Activations Density 0.060%

    No Known Activations