© 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. 104463
    Prev
    Next
    INDEX
    Explanations

    Uncle followed by names or relation descriptions

    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
    '
    -2.72
     красивая
    -2.39
     высокая
    -2.34
    仉
    -2.30
     místa
    -2.28
     nových
    -2.27
    公斤
    -2.27
    嗵
    -2.22
     innehå
    -2.13
     trochu
    -2.11
    POSITIVE LOGITS
    ↵
    3.42
    ྵ
    2.66
    ?’
    2.64
    $
    2.47
     Saltar
    2.41
    ,’
    2.41
    橚
    2.41
    ’?
    2.39
    䉴
    2.38
     são
    2.27
    Activations Density 0.005%

    No Known Activations