© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    slideshow

    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
    2
    -3.00
    0
    -2.84
    6
    -2.73
     \
    -2.61
    4
    -2.59
    7
    -2.58
    3
    -2.36
    9
    -2.23
     provide
    -2.20
    8
    -2.20
    POSITIVE LOGITS
     coloridos
    2.47
    媖
    2.41
     ſeveral
    2.28
     espectaculares
    2.25
     atractivos
    2.25
    </h3>
    2.25
    
    2.23
    宬
    2.23
    —"
    2.13
     fêtes
    2.13
    Activations Density 0.003%

    No Known Activations