© 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. 130533
    Prev
    Next
    INDEX
    Explanations

    logging data and access

    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
    ↵↵
    -3.55
     {
    -2.59
    0
    -2.33
    v
    -2.06
    g
    -2.05
    {
    -1.95
    4
    -1.90
    (
    -1.88
    »
    -1.82
    \
    -1.74
    POSITIVE LOGITS
    に興味
    2.56
     were
    2.17
    鈊
    2.11
    厯
    2.05
     veranstal
    2.05
    ＝＝＝＝
    2.03
    の魅力
    2.00
    
    1.98
     Ә
    1.98
    思索
    1.98
    Activations Density 0.009%

    No Known Activations