© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75653
    Prev
    Next
    INDEX
    Explanations

    Wild West

    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
    \
    -1.76
    不夠
    -1.49
    2
    -1.45
    '
    -1.41
    ニット
    -1.40
    O
    -1.38
    拚
    -1.34
    Is
    -1.32
    []
    -1.31
    first
    -1.30
    POSITIVE LOGITS
    ERSHIP
    1.54
     auriculares
    1.47
     masih
    1.47
    喳
    1.42
    kript
    1.41
    seded
    1.41
     invierno
    1.40
    atica
    1.40
    天井
    1.39
    LabelTagHelper
    1.38
    Activations Density 0.012%

    No Known Activations