© 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. 48036
    Prev
    Next
    INDEX
    Explanations

    electrical wiring and connections

    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
    ’
    -2.34
    $
    -1.98
    ly
    -1.91
    ``
    -1.80
    ская
    -1.80
    cessed
    -1.72
    ing
    -1.62
    ྥ
    -1.62
    '{
    -1.60
    謦
    -1.58
    POSITIVE LOGITS
    ihnachts
    1.59
     resourceful
    1.56
    idjan
    1.55
    矗
    1.55
     телефона
    1.48
     acostumb
    1.47
     anjo
    1.47
     else
    1.47
     Pokud
    1.45
     erfordert
    1.45
    Activations Density 0.017%

    No Known Activations