© 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. 42068
    Prev
    Next
    INDEX
    Explanations

    cafes, bistros, and coffee shops

    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
    </h2>
    -1.80
    1
    -1.72
     About
    -1.52
     nationalen
    -1.48
     について
    -1.48
     größten
    -1.47
    sellors
    -1.47
     Concerning
    -1.45
    aussian
    -1.45
     that
    -1.45
    POSITIVE LOGITS
     simpel
    1.66
    🥱
    1.63
    😐
    1.60
    😪
    1.56
    Café
    1.56
     dahil
    1.55
     accessoires
    1.55
    😧
    1.53
    ☕️
    1.53
    ☘
    1.52
    Activations Density 0.015%

    No Known Activations