© 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. 11906
    Prev
    Next
    INDEX
    Explanations

    central aspect

    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
    {
    -3.86
    ’
    -3.22
    ↵↵
    -2.64
    "));
    -2.52
     of
    -2.27
     extremamente
    -2.23
     Resultat
    -2.16
     imprescin
    -2.05
    是指
    -2.03
    ))){
    -1.98
    POSITIVE LOGITS
    蒹
    3.14
    蛧
    2.61
    ୌ
    2.58
    Однако
    2.55
    配布
    2.48
    what
    2.47
     トマト
    2.42
    焢
    2.42
    most
    2.41
    攻擊
    2.41
    Activations Density 0.011%

    No Known Activations