© 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. 124118
    Prev
    Next
    INDEX
    Explanations

    providing or seeking an answer

    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
     feine
    -2.42
     anhänger
    -2.13
    gives
    -2.08
     bedeckt
    -1.98
    Compared
    -1.96
    ꯳
    -1.95
    Pág
    -1.94
    makes
    -1.92
    Odpovědět
    -1.91
    苤
    -1.91
    POSITIVE LOGITS
    ↵↵
    2.73
    er
    2.67
    p
    2.44
     answer
    2.42
    柃
    2.28
     if
    2.22
    ྜ
    2.22
    m
    2.09
     RSITY
    2.08
    {
    2.08
    Activations Density 0.011%

    No Known Activations