© 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. 60998
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags and similar characters

    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
     segurando
    -1.62
     sofrer
    -1.59
    prés
    -1.59
     olhando
    -1.55
     estabele
    -1.53
    0
    -1.43
     Años
    -1.39
     desempen
    -1.38
     devem
    -1.37
     deverá
    -1.36
    POSITIVE LOGITS
    </h3>
    1.68
    ()},
    1.57
    étricas
    1.45
    curkan
    1.42
    𝓻
    1.41
    ogues
    1.41
    ternut
    1.41
    ñor
    1.38
    termilk
    1.38
    鰨
    1.38
    Activations Density 0.004%

    No Known Activations